Systems and methods for artificial voice generation

Abstract

A breathing-driven speech generation system is capable of producing high-quality artificial speech. The system includes an airflow chamber and a speech chamber, wherein the airflow chamber includes a first opening, a second opening, and a third opening, defining an automatic air passage between the first, second, and third openings; the speech chamber includes an air inlet and a speech outlet, wherein the air inlet of the speech chamber communicates with the third opening of the airflow chamber, and the generated speech exits the speech chamber through the speech outlet. The airflow chamber includes a first movable member that can be adjusted to match the breathing force of different users for easy use, and the speech chamber includes a second movable member that can be customized to generate a range of male / female or non-binary gender speech feature configurations.

Description

Related applications

[0001] This application claims convention priority to Australian provisional patent application AU 2023903513, filed November 1, 2023, and U.S. provisional patent application US 63 / 595,183, filed November 1, 2023. The contents of AU'513 and US'183 are incorporated herein by reference in their entirety. Technical Field

[0002] This invention generally relates to artificial speech generation. In a further example, the invention relates to methods and systems for generating speech. Background Technology

[0003] The larynx, also known as the voice box, is the organ used to produce the sounds humans use to vocalize. The larynx contains the vocal cords, the source of human speech. When a healthy person vocalizes, the sound (or "speech") produced by the vocal cords in the larynx enters the vocal tract, where the speech is filtered (e.g., by controlling the movement of the tongue and lips) to produce a phonation. Figure 1 A). People whose larynx has been surgically removed (through laryngectomy) or bypassed (through tracheostomy) are not paralyzed and may still be able to control their vocal tract, but lack the vocal cords to produce speech. They may also breathe through an opening in their neck (called a stoma). Figure 1 B). Therefore, such individuals are unable to generate speech or have limited speech generation capabilities without artificial assistance.

[0004] One example of an assistive device is the electronic larynx, a handheld device that a laryngectomized patient presses against the skin of his or her neck or face to produce sound. The device functions as an artificial speech source by inducing vibrations within the vocal tract, which the patient can then shape into sound by controlling movements of the tongue and lips. However, the speech produced by the electronic larynx often has a robotic tone, and forcing the patient to manually operate the device while speaking is typically inconvenient.

[0005] During a laryngectomy or tracheostomy, a permanent opening called a stoma is created in the patient's neck or chest to allow breathing (also known as a cervical stoma). Therefore, the patient's trachea is no longer connected to the vocal tract, allowing air from the lungs to exit through the stoma and not enter the vocal tract. A tracheoesophageal vocal prosthesis (TEP) is another commonly used vocal prosthesis (artificial assistive device) for laryngectomy patients. A TEP is a plastic valve surgically inserted into the larynx between the trachea and esophagus. The TEP allows air from the lungs to re-enter the esophagus and travel through the larynx, causing the tissues within the larynx to vibrate, thus producing speech (similar to how sound is produced during a hiccup). While the resulting sound is understandable, the TEP is still a primitive solution and has several key drawbacks. For example, the TEP is highly invasive, posing risks of infection and swallowing hazard, and the produced speech is limited to a hoarse and whisper-like quality. These maintain a similar pitch range for both men and women, effectively making women sound masculine. Furthermore, existing solutions lack the ability to be adapted to the needs of different patients or to have adjustable parameters to suit the needs of different patients.

[0006] Therefore, there is an urgent need for a novel system and / or method for generating speech to help people with speech loss overcome or resolve some of the limitations of existing solutions.

[0007] Any prior publications (or information derived from prior publications) or any known matters mentioned in this specification shall not constitute and should not be construed as an endorsement or acknowledgment, nor shall they constitute and should be construed as any form of implied consent that such prior publications (or information derived from prior publications) or known matters constitute part of the general knowledge in the field covered by this specification.

[0008] Citing Join Each patent, publication or non-patent document mentioned in this application is deemed to be incorporated in its entirety by reference, as if each were incorporated separately.

[0009] Special terms In the following documents, the term "automatic" is defined as the use of a system or part of a system as a hands-free, or system-wide function that does not require manual control or adjustment by the user.

[0010] In the following documents, the term “cervical stoma” is used to refer to an opening in the trachea (airway) on a patient’s neck or chest. Summary of the Invention

[0011] The purpose of this summary is to introduce, in a simplified form, some concepts that will be further elaborated in the following detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter.

[0012] This invention proposes a breath-driven speech generation system and method that is hygienic, non-invasive, and non-surgical, suitable for individuals experiencing aphonia, including those who have undergone laryngectomy or tracheostomy. The invention describes a functional breath-driven artificial speech source capable of generating extremely high-quality speech. Furthermore, the invention proposes a speech generation system that is adjustable to meet different user needs, for example, generating speech with a wide range of adjustable parameters, including male, female, or non-binary gender speech. Those skilled in the art will understand that not all embodiments of the invention encompass all the advantages described above.

[0013] The devices and methods disclosed herein may include an artificial larynx and a method for generating speech in a person who has lost their voice after surgical removal or bypassing of the larynx (including laryngectomy or tracheostomy) using the artificial larynx.

[0014] According to an exemplary aspect, a speech generation system is provided that communicates with a patient's cervical stoma and receives inhaled and exhaled airflow from the stoma. The speech generation system may further include an open speech outlet communicating with the user's oral cavity to generate speech. The user uses the speech generation system as an artificial voice aid or an artificial larynx to generate sounds.

[0015] According to an exemplary aspect, a speech generation system is provided, which may, for example, provide a non-invasive and non-surgical method for generating speech.

[0016] Furthermore, since the speech generation system disclosed in this invention provides a natural exhalation process similar to that of healthy speech generation, users are able to speak without manual intervention.

[0017] According to an exemplary aspect, a speech generation system is provided, which, for example, can provide an artificial larynx capable of automatic bidirectional breathing, enabling subjects to perform manual inhalation and exhalation without the need for device removal.

[0018] According to an exemplary aspect, a speech generation system is provided that, in some examples, can provide an artificial larynx suitable for manual use.

[0019] According to an exemplary aspect, a speech generation system is provided capable of generating speech in a subject. In some examples, the apparatus, system, or method disclosed herein is driven by exhaled airflow to generate speech. In some examples, the apparatus, system, or method disclosed herein utilizes exhaled airflow to generate extremely high-quality speech for a subject. For example, the apparatus and method disclosed herein may provide an artificial larynx capable of generating speech with selective or adjustable parameters (e.g., pitch range, speech spectrum, gender-related speech quality selection, etc.).

[0020] According to an exemplary aspect, a speech generation system is provided that contacts a patient's cervical stoma through a medical-grade barrier to maintain hygiene and stoma safety. The devices, systems, or methods disclosed herein are non-surgical and non-invasive (wearable). In some examples, the devices, systems, or methods disclosed herein can be a hygienic solution that uses a medical-grade respiratory barrier to indirectly contact the patient's cervical stoma to maximize hygiene. In some examples, the devices, systems, or methods disclosed herein are partially or fully washable. In some examples, the devices, systems, or methods disclosed herein include a fully or partially disposable artificial larynx. According to an exemplary aspect, the speech generation system may include disposable and replaceable parts, such as parts that can be detached or discarded at any time, to maximize hygiene. According to an exemplary aspect, the speech generation system does not directly contact the airway or stoma, for example, devices that prevent saliva and bacteria from entering the airway.

[0021] According to an exemplary aspect, a breathing-driven speech generation system is provided, which can be customized to function for different users, including having customizable speech generation parameters to generate male, female, or non-binary gender voices. In some examples, the speech generation system disclosed herein may have customizable parameters, such as adjustable airflow resistance, to provide easy and comfortable use for people with different breathing abilities, including, for example, those with small, medium, or large lung capacity. In some examples, the speech generation system disclosed herein may have customizable parameters that can be adjustable to suit people with different breathing efforts and different lung sizes. In some examples, the speech generation system disclosed herein may have customizable parameters that enable the device to generate speech with a breathing effort close to tidal breathing and comfortable for the user. This allows the device to minimize user fatigue and is suitable for long-term use.

[0022] According to an exemplary aspect, a speech generation system is provided, comprising an airflow chamber (also referred to as an air cavity), wherein the airflow chamber may include at least a first opening, a second opening, and a third opening (air outlet), wherein the first opening of the airflow chamber communicates with a cervical stoma via a medical-grade respiratory barrier. The airflow chamber disclosed herein includes a first movable member (movable air element), wherein the first movable member is configured to act as a multi-directional air valve to guide air within the airflow chamber between the first opening, the second opening, or the air outlet. The airflow chamber and movable air element disclosed herein may provide at least three different modes: 1) automatic inhalation; 2) automatic exhalation (bidirectional breathing), whereby the user can inhale and exhale naturally without removing the device from the stoma; and 3) automatic speech generation. Furthermore, the airflow chamber may also provide additional modes, for example, a bypass mode, wherein the user can disable the speech generation function of the device when coughing or forceful breathing is required without removing the device from the stoma.

[0023] According to an exemplary aspect, the airflow chamber and movable air element of the speech generation system may have adaptive, adjustable, or preset configurable settings, including selective aerodynamic resistance, to make the device suitable for people with a wide range of respiratory dynamics, including, for example, low, medium, or high breathing effort.

[0024] According to an exemplary aspect, the speech generation system includes an airflow cavity configured to communicate with, be sealed to, or contain a medical-grade respiratory barrier, wherein the medical-grade respiratory barrier communicates with a user's cervical stoma. According to an exemplary aspect, the airflow cavity provides hygienically safe communication with the stoma and airway via the medical-grade respiratory barrier to protect the airway from leaks, bacteria, or other contaminants. In some embodiments, the medical-grade respiratory barrier may be a non-separable portion of the airflow cavity. In some embodiments, the medical-grade respiratory barrier may be an attachable or removable portion of the airflow cavity. In some embodiments, the medical-grade respiratory barrier may be detachable from and not part of the airflow cavity, but may be attached to or detachable from the device.

[0025] According to one exemplary aspect, the medical-grade respiratory barrier may be a heat and moisture exchanger (HME), including, for example, an HME disc or HME box used by a laryngectomy patient. According to another exemplary aspect, the HME disc or HME box may be part of a speech generation system and contained within an airflow cavity, or may be separate from the airflow cavity and may be attached to or detached from the airflow cavity.

[0026] According to an exemplary aspect, a speech generation system is provided, the system including an airflow cavity, wherein the airflow cavity may be attached to or comprise a medical-grade respiratory barrier, wherein the medical-grade respiratory barrier is coupled to an ostomy using an ostomy accessory. In some embodiments, the ostomy accessory may be part of a device. In some embodiments, the ostomy accessory may be detachable and is not part of the device.

[0027] According to an exemplary aspect, the stoma accessory may include, for example, an adhesive substrate that can be attached to the skin around the stoma in a human subject's neck, including, for example, a laryngectomy baseplate. In other examples, the stoma accessory substrate may be partially or deeply inserted into the stoma, such as a laryngectomy tube or tracheostomy tube widely used by laryngectomy, laryngectomy-button, or laryngectomy or tracheostomy patients.

[0028] According to an exemplary aspect, the speech generation system includes an airflow cavity configured to communicate with, seal with, or contain a medical-grade respiratory barrier. In some embodiments, the airflow cavity connected to its medical-grade barrier can be easily detached from the rest of the speech generation system. This facilitates portability of the device. In some embodiments, the airflow cavity connected to its medical-grade barrier can be easily detached from the rest of the speech generation system, wherein the airflow cavity connected to its medical-grade barrier can remain on the stoma without removing it from communication with the stoma. This provides additional stoma safety for the device.

[0029] According to an exemplary aspect, the speech generation system includes a speech cavity with an air inlet and a speech outlet, wherein the air inlet of the speech cavity is connected to the air outlet of an airflow cavity, and the speech outlet of the speech cavity is connected to the user's oral cavity, wherein the speech cavity includes a second movable member (movable speech member) that generates sound based on air exiting the air outlet of the airflow cavity, wherein the generated speech exits the speech cavity via the speech outlet to stimulate the user's oral cavity.

[0030] According to an exemplary aspect, the speech generation system includes a speech cavity comprising a movable speech component capable of generating extremely high-quality speech with near-natural sound. In some embodiments, the speech cavity and the movable speech component have customizable parameters that can be adjusted to generate a wide range of extremely high-quality speech for males. In some embodiments, the parameters of the speech cavity and the movable speech component can be adjusted to generate a wide range of extremely high-quality speech for females. In some embodiments, the parameters of the speech cavity and the movable speech component can be adjusted to generate a wide range of extremely high-quality speech for non-binary gender speech.

[0031] According to an exemplary aspect, the speech cavity and movable speech component can generate a flat or semi-flat spectrum (spanning a frequency range of any value between 70 Hz and 200 Hz, 70 Hz and 300 Hz, or 70 Hz and 300 Hz and 1500 Hz, with harmonic peak amplitudes varying from + / -2 dB to + / -3 dB to + / -4 dB to + / -5 dB to + / -6 dB). In some embodiments, the flat or semi-flat spectrum of the proposed speech generation system enables the user to generate highly intelligible speech. In some embodiments, the flexibility and shape of the movable speech component can be adjusted for the fundamental frequency of the source's harmonic spectrum to span from male (70-150 Hz) to non-binary gender (130-160 Hz) to female (160-240 Hz) and higher values ​​for children.

[0032] According to an exemplary aspect, the speech cavity or movable speech component may provide adaptive, adjustable, or preset speech generation parameters, including selective, adjustable, or preset fundamental frequency ranges to generate male, female, or non-binary gender speech, or selective spectral features to improve the clarity of the user's speech.

[0033] According to an exemplary aspect, the voice cavity or movable voice component can provide customizable, adaptive, or preset parameters configured to match the breathing characteristics of different individuals. For example, in some embodiments, the voice cavity or movable voice component parameters can be configured by adjusting the aerodynamic resistance of the device to match the breathing effort of different individuals during vocalization, thereby generating speech with a breathing effort close to tidal breathing that is comfortable for the user. This allows the device to minimize user fatigue and is suitable for long-term use.

[0034] According to an exemplary aspect, a speech generation system including the devices and methods disclosed herein can provide an artificial larynx that can be used without manual intervention (e.g., when worn as an earphone around the ear, or when worn in a neck strap around or behind the neck), wherein the multi-directional valve function of the medical-grade breathing barrier and air chamber (also known as an airflow chamber) enables the device to remain connected to the stoma without manual intervention.

[0035] According to an exemplary aspect, the speech generation system disclosed herein includes an artificial larynx capable of generating speech in a subject; and a method of generating phonation in a subject using the artificial larynx. The device disclosed herein provides a hygienic and safe method of communicating with an airway via a cervical stoma, wherein a medical-grade respiratory barrier acts as an interface to protect the airway from dust, saliva, bacteria, or other potential contaminants.

[0036] According to an exemplary aspect, the speech generation system discloses a miniature, removable, and portable artificial larynx. The devices disclosed herein may include an artificial larynx that can be detached from a cervical stoma or stoma accessory when needed.

[0037] According to an exemplary aspect, the speech generation system disclosed herein includes an air cavity that is adjustable to seal on or adapt to individuals with different stoma shapes and structures, wherein the device adapts to stomas of different shapes in such a way as: a) Through stoma attachments that are attached to the skin or inserted into the stoma. These provide a connection between the airway and its medical-grade respiratory barrier and a standard orifice, or b) A compressible first opening through an air cavity sealed on the stoma of different users.

[0038] According to an exemplary aspect, the voice generation system provides a pathway for exhaled airflow, which naturally contains moisture, potentially leading to condensation within the device. In some embodiments, the device may include automated or manual condensation removal methods, including, for example, a humidity sensor or a moisture trap (also known as a water trap), for removing, capturing, or containing condensed water droplets internally. In some embodiments, the device may include a hydrophobic coating on an inner surface to prevent the formation of condensed droplets and obscuring the device. In some embodiments, the device may include thermal insulation to prevent condensation. In some embodiments, the device may be made of a selective, semi-permeable, or breathable material that can transport water vapor, condensate, and accumulated moisture to the surrounding environment, thereby reducing or preventing condensation.

[0039] According to an exemplary aspect, the speech generation system can provide convenient replacement of the first or second movable component.

[0040] According to an exemplary aspect of the speech generation system, the first or second movable component may be a flexible membrane (referred to as an air membrane and a speech membrane, respectively) having customizable parameters, including, for example, material, flexibility, shape, or thickness.

[0041] According to an exemplary aspect, the speech generation system can provide a mechanism to prevent speech diaphragm blockage due to additional pressure buildup within the speech cavity.

[0042] The apparatus and methods disclosed herein describe a speech generation system having adjustable, preset, or adaptive parameters that can be adjusted according to user needs, including, for example, adaptive parameters for speech generation and breathing effort availability for a wide range of users. Any of these parameters (including, for example, a wide range of pitch values ​​or aerodynamic drag of the device for men, women, or children) can be adjusted according to user needs or can be adjusted to provide specific comfort for different individuals. Any of these parameters can be provided in adaptive, adjustable, or preset values ​​and settings. In this disclosure, these or preset values ​​are referred to as “quantized” values. For example, the pitch range of the device can be preset (quantized) to four levels: male, female, non-binary gender, or child, or quantized to include a more detailed pitch range. Similarly, in some embodiments, the breathing effort of the device can be quantized as low, medium, or high. The speech generation system can have functional, clinically validated, adjustable, or preset (quantized) parameters to make the device comfortable for a wide range of users.

[0043] Other aspects, features, and advantages will become apparent when reading the following detailed description in conjunction with the accompanying drawings, which are part of this disclosure and illustrate the principles of various embodiments by way of example. Attached Figure Description

[0044] Figure 1 The illustration shows a healthy person (A) and an exemplary person (B) who has lost their larynx due to a laryngectomy and breathes through a stoma (which may be located on the user's neck or chest and connected to their airway).

[0045] Figure 2A A first general embodiment of the speech generation system 100 disclosed herein is shown, the system including an airflow cavity 100AC and a speech cavity 100VC, wherein the airflow cavity 100AC is in communication with a medical-grade respiratory barrier. The speech generation system 100 also includes an open-mouth speech outlet 100c in communication with the oral cavity.

[0046] Figure 2B A second general embodiment of the speech generation system 100 disclosed herein is shown, the system including an airflow cavity 100AC and a speech cavity 100VC, wherein the airflow cavity 100AC includes a medical-grade respiratory barrier 105 and is in communication with an ostomy or ostomy accessory. The speech generation system 100 also includes an open speech outlet 100c in communication with the oral cavity.

[0047] Figure 2CA third general embodiment of a speech generation system 100 is shown, the system including an airflow cavity 100AC and a speech cavity 100VC, wherein the speech generation system 100 further includes a medical-grade respiratory barrier 105 and a medical-grade stoma accessory 130, wherein the stoma accessory 130 is in communication with a stoma. The speech generation system 100 also includes an open-mouth speech outlet 100c in communication with the oral cavity.

[0048] Figure 3 illustrates an exemplary ostomy accessory method that may or may not be part of the speech generation system 100, including: Figure 3A -Ostomy attachments using adhesive substrates; and Figure 3B -Ostomy attachment using an insertable substrate.

[0049] Figure 4 shows an exemplary embodiment of the airflow chamber 100AC. Figure 4A The assembled airflow chamber 100AC is shown, which includes an airflow chamber housing 1000_AC, a first opening 100a (air inlet / air outlet), a second opening 100b (air inlet / air outlet), and a third opening 100AC_c (air outlet). Figure 4A It also shows, for example, the fourth opening 100AC_d (air vent). Figure 4B A disassembly embodiment of the airflow chamber housing 1000_AC is shown.

[0050] Figure 5 illustrates an exemplary embodiment of the assembly of the airflow chamber 100AC, which has an ostomy attachment 200 and a medical-grade respiratory barrier, which may be part of the device 105 or may be independent of the device 205. Figure 5A An exemplary airflow chamber 100AC is shown in a disassembled view, and Figure 5B The corresponding assembly view is shown.

[0051] Figure 6 shows an assembly example of an airflow chamber 100AC with a medical-grade respiratory barrier 105 (shaded), wherein the barrier 105 is in Figure 6A It is embedded as an inseparable part of the device. Figure 6B An example of an airflow chamber 100AC is shown, wherein the airflow chamber 100AC can be opened to contain a detachable and removable medical-grade respiratory barrier, which may be part of device 105 or may be independent of device 205.

[0052] Figure 7 shows an example of a speech cavity air film 110, which can be placed within the airflow cavity housing 1000_AC. Figure 7A In one embodiment, the air film 110 is a circular disc made of a flexible material, such as a thin silicone film, which is fixed on and inside the breathable surface 1000_AC_b. Figure 7B A disassembled version of the air film inside the airflow chamber is shown.

[0053] Figure 8 illustrates an exemplary embodiment of the air film 110 and how it can move in response to inhalation / exhalation, with arrows indicating the corresponding directions of inhaled / exhaled air. Figure 8A An example of an air membrane 110 is shown, in which a strong exhaled air pushes the membrane to close the opening 100b, and the membrane guides air out from the outlet 100AC_c. Figure 8B The membrane position during normal tidal inhalation / exhalation is shown, wherein the membrane is bent inward so that it allows inhaled and exhaled airflow through opening 100b.

[0054] Figure 9 illustrates an exemplary embodiment of the airflow cavity, wherein the airflow cavity has a stable housing for placement on the stoma, and includes a medical-grade airway barrier for protecting the airway during or after speech generation. Figure 9A ); and a detachable housing (which includes a movable gas element 110; not shown) Figure 9B ). Figure 9C This is the assembled version of this embodiment when attached to the stoma accessory.

[0055] Figure 10 An exemplary embodiment of the airflow cavity is shown, wherein the voice outlet 100AC_c can be detached via, for example, a magnetically detachable connector, thereby enabling portable use of the voice generation system 100.

[0056] Figure 11 An exemplary embodiment of the airflow chamber is shown, which has a closed water trap 100_AC_WT for decondensation.

[0057] Figure 12 is an exemplary embodiment of an airflow duct 133 that provides communication between an airflow chamber 100AC and a voice chamber 100VC.

[0058] Figure 13 A preferred embodiment of the speech generation system 100 is shown, wherein all modules are assembled and communicate with the trachea and mouth in the neck, and wherein the system may or may not be manual. The figure is an example of a speech generation system 100 with a manual-free function that eliminates the need for the user to manually hold the device.

[0059] Figure 14 An exemplary embodiment of a speech cavity 100VC and an oral adapter 100d is shown, the oral adapter being connected to a user's oral cavity.

[0060] Figure 15 A preferred assembly embodiment of the speech generation system 100 is shown, wherein the air membrane 110 and the speech membrane 120 interact together to provide the system with a bidirectional breathing and speech generation pattern.

[0061] Figure 16 shows an exemplary embodiment of the speaker cavity (also known as the voice cavity) 100VC. Figure 16A The speaker cavity 100VC is shown, which includes a first opening 100VC_a and a second opening (open-type speech outlet) 100c (which can communicate with the inlet) and a membrane retainer 120VC. Figure 16B The image shows the movement of air inside the speaker enclosure, with arrows indicating the direction of air movement. Figure 16C An exemplary implementation of the speech diaphragm 120 is shown.

[0062] Figure 17A An exemplary embodiment of a voice diaphragm 120 is shown, which has a disc shape and is fixed to a diaphragm holder 120VC, wherein the diaphragm is located within the diaphragm holder in a rest position (where the central portion is free and ready to vibrate). Figure 17B An exemplary embodiment is shown, wherein the membrane retainer 120VC includes a mesh structure 1203VC to convert a potential jet flow within the device into a laminar flow of air suitable for generating a stabilizing force to vibrate the membrane 120, wherein the arrow indicates the direction of air movement.

[0063] Figure 18 illustrates an exemplary embodiment of the membrane retainer 120VC, which is configured to generate, for example, male or female speech. Figure 18A An example of a membrane retainer for a female voice is shown. Figure 18B An example of a membrane retainer for a male voice is shown.

[0064] Figure 19 An example of a flat / semi-flat harmonic spectrum measured by the speech generation system 100 is shown, which has resulted in extremely high speech quality for the user.

[0065] Figure 20 illustrates a preferred embodiment of the speech generation system 100, which provides manual-free functionality. Figure 20A In one embodiment, the voice cavity 100VC is designed to be fixed on or around the ear as an earphone, wherein the airflow cavity 100AC is in communication with the user's cervical stoma. Figure 20B This shows what it looks like when worn on a user's ear. Figure 20A Examples of implementations.

[0066] Figures 21-24 illustrate a preferred embodiment of the medical-grade respiratory barrier 105 as implemented as a heat and moisture exchanger or HME (HM100), which may be part of a speech generation system.

[0067] Specifically, Figure 21 shows an exemplary medical-grade respiratory barrier 105 as an HME box (HM100), which is located between medical-grade stoma attachments 130 and is compatible with the different diameters of these stoma attachments 130. Figure 21AAn exemplary HME compatible with stoma attachment 130 of 22 mm or 23 mm diameter is shown. The HME box (HM100) can be rotated for use with stoma attachment 130, wherein the compatible diameter is at one end of the HME and the air cavity is connected to the other end of the HME. Figure 21B The HME box (HM100) is shown, wherein the upper and lower parts (HM100u and HM100d, respectively) can be detached to contain HME foam (HM1001 heat-absorbing and moisture-absorbing material).

[0068] Figure 22 shows an example of an HME box (HM100) containing a barrier HM1002 to prevent or redirect sputum / mucus produced in the stoma during, for example, coughing, from exiting the stoma, so that these do not clog the HME foam HM1001 and enable breathing through the foam to be unobstructed by sputum / mucus. Figure 22B The various parts of the design are shown, and Figure 22C The illustration shows how the box (HM100) is located between the airflow chamber 100AC and the medical-grade stoma accessory 130.

[0069] Figure 23 An example of how the HME (HM100) can be customized to connect to the airflow chamber 100AC is shown. The airflow chamber can be designed to attach to or detach from an existing HME. Alternatively, as shown, the device can be customized to fit its own HME.

[0070] Figure 24 Another example of how the airflow chamber 100AC and the HME box HM100 can be connected is shown, wherein the HM100 can be attached to or detached from the airflow chamber via a threaded mechanism (100AC_tr). Detailed Implementation

[0071] The following patterns are described by way of example only to provide a more precise understanding of the subject matter of one or more embodiments of the invention. In the figures incorporated to illustrate features of exemplary embodiments, the same reference numerals are used to identify the same parts in the figures.

[0072] This invention describes a breathing-driven speech generation system that generates speech components and / or airflow components for a user. The system acts as an artificial speech (and / or airflow) source for the user, replacing the speech generation function of the vocal cords. The system can generate extremely high-quality speech for aphoniac individuals who may have lost their larynx, suffered laryngeal injury, or had their larynx bypassed, including but not limited to those who have undergone laryngectomy or tracheostomy.

[0073] The following will refer to Figure 2A and 2B 2C describes a general embodiment of the speech generation system.

[0074] refer to Figure 2A The image shows a speech generation system 100, which includes at least a first opening 100a, a second opening 100b, and a third opening 100c. The first opening 100a and the second opening 100b serve as air inlets / outlets, while the third opening 100c serves as an open speech outlet. (Reference) Figure 2A The image shows a speech generation system 100, wherein a first opening is connected to a user's cervical stoma, a second opening 100b is connected to open air, and a third opening 100c is connected to the user's oral cavity.

[0075] refer to Figure 2A In a typical embodiment, the first opening of the speech generation system 100 may be connected to the stoma via a medical-grade barrier 205, which is not part of the device.

[0076] The speech generation system 100 further includes an airflow cavity 100AC and a speech cavity 100VC, wherein the airflow cavity 100AC is in communication with a first opening 100a, a second opening 100b, and the speech cavity 100VC. The speech generation system 100 also includes a speech cavity 100VC, which is in communication with the airflow cavity 100AC and a third opening 100c. The speech generation system 100 further includes and defines an air passage, airflow channel, or airflow duct 133 for moving air from the air cavity to the speech cavity, and a bidirectional air passage, airflow channel, or air duct 144 for transmitting air between the air cavity AC and the third opening 100c.

[0077] refer to Figure 2A The diagram illustrates a speech generation system 100, wherein an airflow chamber 100AC further includes a first opening 100a (air inlet / outlet), a second opening 100b (air inlet / outlet), and a third opening (outlet) 100AC_c. The airflow chamber 100AC also includes an airflow movable member 110, which acts as a multi-directional air valve within the airflow chamber 110 and redirects air between the first opening 100a, the second opening 100b, and the outlet 100AC_c.

[0078] exist Figure 2A In some embodiments, the first opening 100a of the airflow chamber communicates with the patient's cervical stoma via a medical-grade respiratory barrier (not part of the device) serving as an interface, and receives and accesses inhaled and exhaled airflow from the stoma through the first opening 100a. In some embodiments, the second opening 100b of the airflow chamber may communicate with and receive open air, and the third opening 100AC_c of the airflow chamber communicates with the speech cavity via an airflow duct 133.

[0079] Figure 2AThe speech generation system 100 also includes and defines an air passage, airflow channel or airflow duct 133, which moves air from the third opening (outlet) 100AC_c of the airflow cavity to the speech cavity.

[0080] refer to Figure 2A The image shows a speech generation system 100, wherein the speech cavity 100VC further includes a speech movable member 120, wherein the speech movable member 120 is configured to vibrate in response to air flowing into the speech cavity 100VC.

[0081] exist Figure 2A In a general embodiment, the voice movable member 120 generates voice in response to changes in air pressure at the first opening 100a and the third opening 100c of the voice generation system 100. (See reference...) Figure 2A The pressure at or near the first opening 100a corresponds to the breathing pressure at or near the cervical stoma, and the pressure at or near the third opening 100c corresponds to the breathing pressure in or near the user's mouth.

[0082] refer to Figure 2A The image shows a speech generation system 100, which includes an airflow cavity 100AC, wherein a first opening 100a of the airflow cavity is in communication with a medical-grade respiratory barrier 205, and the medical-grade respiratory barrier 205 is in communication with an ostomy. Figure 2A In some embodiments, the first opening 100a of the airflow cavity may be attached to or detached from the medical-grade respiratory barrier 205, wherein the medical-grade respiratory barrier is not part of the device and is disposable and replaceable. Figure 2A In some embodiments, the first opening 100a of the airflow cavity can be sealed onto a medical-grade respiratory barrier 205, wherein the medical-grade respiratory barrier is not part of the device and is disposable and replaceable. Figure 2A In some embodiments, the speech generation system 100 does not come into direct contact with the stoma, because the medical-grade respiratory barrier acts as the interface between the first opening 100a and any communication with the stoma.

[0083] refer to Figure 2B A general embodiment of the speech generation system 100 is shown, which includes at least a first opening 100a (air inlet / outlet), a second opening 100b (air inlet / outlet), and a third opening 100c, the third opening serving as an open-ended speech outlet. (See reference...) Figure 2B The diagram illustrates a speech generation system 100, wherein a first opening communicates with a cervical stoma and receives inhaled and exhaled airflow from the stoma. A second opening 100b communicates with open air, and a third opening 100c communicates with the user's oral cavity.

[0084] refer to Figure 2BIn a general embodiment, the first opening 100a of the speech generation system 100 may communicate with the stoma via a medical-grade barrier 205 included as part of the device.

[0085] refer to Figure 2B In a general embodiment, the speech generation system 100 further includes an airflow cavity 100AC and a speech cavity 100VC, wherein the airflow cavity 100AC is in communication with a first opening 100a, a second opening 100b, and the speech cavity 100VC. The speech generation system 100 also includes a speech cavity 100VC, which is in communication with the airflow cavity 100AC and a third opening 100c. The speech generation system 100 further includes and defines an air passage, air channel, or airflow duct (also called a flow tube) 133 for moving air from the airflow cavity 100AC to the speech cavity, and a bidirectional air passage, air channel, or air duct 144 for guiding air between the airflow cavity AC and the third opening 100c. The speech generation system 100 also includes a first opening 100a and a second opening 100b serving as an air inlet / outlet, and a third opening 100c (an open speech outlet) serving as a speech outlet communicating with the user's mouth, such that during use, the air pressure at or near the speech outlet 100c corresponds to the air pressure within the user's mouth.

[0086] refer to Figure 2B The diagram illustrates a speech generation system 100, wherein an airflow chamber 100AC further includes a first opening 100a, a second opening 100b, and a third opening (exit) 100AC_c. The airflow chamber 100AC also includes a medical-grade respiratory barrier 105 and an airflow movable member 110, wherein the airflow movable member 110 is configured to redirect air within the airflow chamber 110 as a multi-directional air valve between the first opening 100a (inlet / outlet), the second opening 100b (inlet / outlet), or the third opening (exit) 100AC_c.

[0087] exist Figure 2B In a general embodiment, the first opening 100a of the airflow cavity communicates with the patient's cervical stoma via a medical-grade respiratory barrier 105 contained within or as part of the airflow cavity, wherein the medical-grade respiratory barrier 105 serves as an interface for the airflow cavity to receive and access the airflow inhaled and exhaled through the stoma. In some embodiments, the second opening 100b of the airflow cavity may communicate with and receive open air, and the third opening 100AC_c of the airflow cavity communicates with the speech cavity via an airflow duct 133.

[0088] refer to Figure 2B In a general embodiment, the speech generation system 100 further includes and defines an air passage, airflow channel, or airflow duct 133, which moves air from the third opening (outlet) 100AC_c of the air cavity to the speech cavity.

[0089] exist Figure 2B In a general embodiment, the voice movable member 120 generates voice in response to changes in air pressure at the first opening 100a and the third opening 100c of the voice generation system 100. (See reference...) Figure 2A The pressure at or near the first opening 100a corresponds to the breathing pressure at or near the cervical stoma, and the pressure at or near the third opening 100c corresponds to the breathing pressure in or near the user's mouth.

[0090] refer to Figure 2B The speech generation system 100 also includes a medical-grade respiratory barrier 105, which is part of and contained therein, wherein airflow entering and exiting from the first opening 100a passes through the medical-grade respiratory barrier 105 before entering the rest of the system, because the medical-grade respiratory barrier provides safe and hygienic communication with the stoma.

[0091] refer to Figure 2B An exemplary speech generation system 100 is illustrated, wherein a medical-grade respiratory barrier 105 is implemented as a permanent part of an airflow cavity 100AC, wherein the airflow cavity 100AC and the medical-grade respiratory barrier contained therein can be frequently (e.g., daily) removed or discarded for hygienic use of the device. Figure 2B In some examples, a medical-grade respiratory barrier 105 is included within an airflow chamber 100AC, but it is a non-permanent, attachable, detachable, or disposable portion of the airflow chamber, wherein the included medical-grade respiratory barrier can be frequently (e.g., daily) removed or discarded for hygienic use, while the airflow chamber can be cleaned and reused for a longer period. Figure 2B In some examples, a medical-grade airway barrier is used, with the first opening 100a communicating with the stoma of the aphoniac patient. This included medical-grade airway barrier is a non-permanent, disposable, and removable part of the airflow chamber 100AC. For example, this could be a disposable medical-grade airway barrier 105 used by the patient to protect their stoma, which can be included in or removed from the airflow chamber 100AC.

[0092] exist Figure 2B In some embodiments of the speech generation system 100, the airflow cavity and its contained medical-grade respiratory barrier 105 may be directly connected to the stoma. Figure 2B In some embodiments of the speech generation system 100, the airflow cavity and its contained medical-grade respiratory barrier 105 may be in communication with stoma attachments, wherein the medical-grade respiratory barrier is attached to or detached from the stoma attachments. Figure 2BIn some embodiments of the speech generation system 100, the airflow cavity and its contained medical-grade respiratory barrier 105 may be in communication with an ostomy accessory, wherein the medical-grade respiratory barrier is sealed to the ostomy accessory. Figure 2B In some embodiments of the speech generation system 100, the airflow cavity and its contained medical-grade respiratory barrier 105 may be in communication with stoma attachments, wherein the airflow cavity is connected to or partially penetrates the stoma attachments.

[0093] refer to Figure 2C This illustrates another general embodiment of the speech generation system and method 100, which includes... Figure 2A and Figure 2B Some or all of the components. Reference Figure 2C In a general embodiment, the first opening 100a of the speech generation system 100 disclosed in this invention may communicate with the stoma via a medical-grade barrier 205 included as part of the device. (See reference...) Figure 2C In an exemplary embodiment, the speech generation system may further include a medical-grade stoma accessory 130 incorporated as part of the device.

[0094] Figure 2C A typical embodiment also includes a medical-grade stoma accessory 130, incorporated as part of the speech generation system 100, for covering the system or connecting the system to a patient's stoma. (See reference...) Figure 2C The image shows a speech generation system 100, whose first opening 100a communicates with a medical-grade stoma accessory 130, which is part of a device, wherein a patient uses the stoma accessory 130 to cover the device or to connect the device to their stoma. (Reference) Figure 2C The image shows a speech generation system 100, whose first opening 100a is connected to a medical-grade stoma accessory 130, which is part of the device. (Reference) Figure 2C The speech generation system 100 comes into direct contact with the stoma via the stoma accessory 130, which is part of the device. (Reference) Figure 2C The voice generation system 100 also includes a medical-grade respiratory barrier 105 to maintain a safe and hygienic connection with the stoma.

[0095] In such Figure 2C In some embodiments shown, the stoma accessory 130 may include a medical-grade accessory or substrate included in the speech generation system and method 100 for covering the device or connecting the device to the stoma, wherein the substrate is attached to the skin around the stoma in the human subject's neck. The stoma accessory substrate 130 may include self-adhesiveness, wherein the substrate is attached to the skin around the stoma in the human subject's neck, similar to, for example, a laryngectomy baseplate. Figure 2CIn some of the described embodiments, the stoma accessory 130 may include a medical-grade accessory or substrate that may partially or deeply penetrate the stoma, such as a laryngectomy, laryngostomy button, or laryngostomy tube. In some embodiments, the substrate 130 may have an extension that partially penetrates the cervical stoma, similar to a tracheostomy tube widely used by tracheostomy patients. In some embodiments, the substrate 130 may be disposable after use and may be frequently (e.g., daily) replaced for hygienic use of the device.

[0096] Referring to exemplary embodiments, a general embodiment of the speech generation system 100 disclosed in this invention includes an airflow cavity 100AC, an air duct 133, a speech cavity 100VC, and an oral cavity adapter 100d.

[0097] The following patterns are described only as examples to provide more precise details about the different components of the subject matter of the speech generation system 100 and one or more embodiments thereof.

[0098] Connection with stoma Referring to Figure 3, patients who have undergone laryngectomy or tracheostomy and are using the speech generation system 100 can use an ostomy accessory substrate to cover or protect their stoma, or to attach the device to their stoma. Figure 3 shows some examples of ostomy accessories that can be used by patients who have undergone laryngectomy or tracheostomy to attach the speech generation system 100 to their stoma. Figure 3A The device includes an adhesive stoma attachment, wherein the stoma attachment substrate 200a is attached to the skin around the stoma in the neck of a human subject. The stoma attachment 200 may include a self-adhesive substrate that attaches to the skin around the stoma in the neck of the subject, including or similar to, for example, a laryngectomy baseplate. Figure 3B In some of the depicted examples, the stoma accessory substrate can be partially or deeply inserted into the stoma, such as in laryngectomy, laryngostomy button, or laryngostomy tube. Figure 3B In some examples, the substrate may have an extension that partially penetrates the cervical stoma, including but not limited to tracheostomy tubes widely used by tracheostomy users.

[0099] In some examples, the stoma accessory substrate may include a connection port 210 configured to receive and retain a medical-grade respiratory barrier 205 to protect the stoma and airway from external particles such as dust or bacteria. In some embodiments, the medical-grade respiratory barrier 205 may be a heat and moisture exchanger (HME).

[0100] Referring to the speech generation system 100, in some embodiments, the first opening 100a of the speech generation system 100 is connected to the patient's cervical stoma via communication with the stoma accessory 200. Figure 2AIn some exemplary embodiments of 2B, the stoma accessory 200 may be commercially available and not part of the device, for example, a laryngostomy button or baseplate, or a tracheostomy tube used by patients undergoing laryngectomy or tracheostomy. Figure 2C In some exemplary embodiments shown, the stoma attachment 130 is included in and is part of the speech generation system 100.

[0101] refer to Figure 2A In some embodiments, the speech generation system 100 has a first opening 100a communicating with an ostomy attachment 200, wherein the ostomy attachment 200 is connected to a medical-grade airway barrier 205, wherein the ostomy attachment 200 and the medical-grade airway barrier 205 are commercially available, separate devices and not part of the device. In some embodiments, the ostomy attachment may include an adhesive substrate attached to the skin around the ostomy in the neck of a human subject. In some embodiments, the substrate may include a self-adhesive material attached to the skin around the ostomy in the neck of a human subject, including, for example, a laryngectomy baseplate. Figure 3A In some embodiments, the substrate may be partially or deeply inserted into the stoma, such as a laryngostomy button. Figure 3B This could be a laryngostomy tube or a stoma tube. In some embodiments, the substrate may have an extension that partially penetrates the cervical stoma, such as a tracheostomy tube widely used by tracheostomy patients. In some examples, the stoma accessory 200 substrate may include a connection port 210 configured to retain a medical-grade respiratory barrier 205 to protect the stoma and airway from external particles such as dust or bacteria. In some embodiments, the medical-grade respiratory barrier device may be a heat and moisture exchanger (HME), including a hands-free HME disc for connecting other devices to the cervical stoma.

[0102] refer to Figure 2A In some embodiments, the speech generation system 100 includes a first opening 100a communicating with the stoma, wherein the first opening 100a is positioned around and outside the stoma accessory 200 without being physically connected to the stoma. In some embodiments, when the stoma accessory opening 210 is connected to the medical respiratory barrier 205 to cover the stoma, the first opening 100a is positioned around and outside the stoma accessory 200. In some embodiments, when the stoma accessory opening 210 is connected to the medical respiratory barrier 205, the first opening 100a is sealed to the stoma or stoma accessory, and the first opening 100a is not directly connected to or attached to the stoma accessory 200, the stoma accessory opening 210, or the medical respiratory barrier 205. Reference Figure 2A In some embodiments, when the stoma attachment is connected to the medical breathing barrier 205 without directly contacting the stoma attachment 200 or the medical breathing barrier 205, the first opening 100a is positioned around the stoma attachment 200.

[0103] refer to Figure 2A The speech generation system 100 includes a first opening 100a communicating with an ostomy. In some embodiments, the first opening 100a communicates with the ostomy, wherein the ostomy is covered by an ostomy attachment 200 connected to a medical-grade barrier 205 that is not part of the device. In some embodiments, the first opening 100a of the speech generation system 100 receives and remains directly attached to the medical-grade barrier 205 (not part of the device). In some embodiments, the first opening 100a may be attached to or detached from the medical barrier (not part of the device) as needed.

[0104] refer to Figure 2A The voice generation system 100 can be sealed, clipped, or connected to a medical-grade barrier 205 (not part of the device), wherein the medical-grade barrier 205 can, for example, be connected to or coupled to or sealed to the stoma accessory opening 210. Reference Figure 2A In some embodiments, the speech generation system 100 uses a medical-grade barrier 205 as an interface to maintain a direct and hygienic connection with the stoma accessory. (See reference...) Figure 2A In some embodiments, the speech generation system 100 uses a medical-grade barrier 205 as a secure interface to maintain a direct and hygienic connection with the stoma accessory, wherein the medical-grade barrier 205 is connected to the speech generation system 100, the first opening, and the stoma accessory orifice 210. (See reference...) Figure 2A In some embodiments of the speech generation system 100, the medical-grade barrier 205 and stoma accessories are not part of the device and are disposable and replaceable after use to maximize hygiene. (See reference) Figure 2A In some embodiments, a medical-grade barrier 205 is used as the interface, and the voice generation system 100 does not directly contact the airway to maximize its safety and hygiene. (Reference) Figure 2A In some embodiments, the speech generation system 100 uses a medical-grade barrier 205 to maintain a direct and hygienic connection with the stoma accessory, wherein the medical-grade barrier 205 is an HME. (See reference...) Figure 2A In some embodiments, the medical-grade respiratory barrier includes a hands-free HME box for connecting other hands-free devices to stoma attachments for people who have undergone laryngectomy or tracheostomy.

[0105] refer to Figure 2AIn some embodiments, the speech generation system 100 uses an external medical-grade barrier 205 as an interface to maintain a direct and hygienic connection with the stoma, wherein exhaled air exiting the stoma through the first opening 100a first passes through the medical-grade barrier 205 (not part of the device) before entering the rest of the speech generation system 100. In some embodiments, the speech generation system 100 uses an external medical-grade barrier 205 as an interface to maintain a direct and hygienic connection with the stoma, wherein inhaled air through the speech generation system 100 first passes through the medical-grade barrier before entering the stoma.

[0106] refer to Figure 2A In some embodiments, the speech generation system 100 disclosed herein includes a first opening 100a that is adjustable to accommodate a medical-grade respiratory barrier 205 (not part of the device). This medical-grade respiratory barrier is adaptable to stoma accessory 200 substrates with different orifice sizes 210 and various stoma accessories, including, for example, adhesive or penetrating stoma accessories. This makes the device widely applicable to individuals with different stoma shapes, sizes, locations, and bone structures.

[0107] refer to Figure 2B The speech generation system 100 includes a medical-grade barrier, which is contained within or located within the device as part of the device. (Reference) Figure 2B The voice generation system 100 includes a medical-grade barrier 105, which is implemented as a permanent part of the device. (Reference) Figure 2B The voice generation system 100 includes a medical-grade barrier 105, which is implemented as a disposable part of the device after it is usable.

[0108] refer to Figure 2B The speech generation system 100 includes a medical-grade barrier 105, which is part of the device and communicates with a first opening 100a, which communicates with a stoma. In some embodiments, the first opening 100a communicates with a stoma, wherein the stoma is covered by a stoma accessory 200, which is not part of the device.

[0109] refer to Figure 2B In some embodiments, the speech generation system 100 includes a medical-grade barrier 105, which is part of the device and communicates with a first opening 100a, wherein the first opening 100a is located around and outside the stoma, but not physically connected to the stoma. In some embodiments, the first opening 100a is located around and outside the stoma, wherein the first opening 100a is not directly attached to the stoma.

[0110] refer to Figure 2BThe speech generation system 100 includes a medical-grade barrier 105, which is part of the device and communicates with a first opening 100a, wherein the first opening 100a communicates with an ostomy accessory 200. Figure 2B In some embodiments, the speech generation system 100 seals, clips, or penetrates the stoma accessory opening 210, wherein the stoma accessory (not part of the device) may include an adhesive substrate that is attached to the skin around the stoma in the neck of the human subject. Figure 2B In some embodiments, the first opening 100a seals, clips, or penetrates the stoma accessory opening 210, wherein the stoma accessory (not part of the device) may include self-adhesiveness, wherein the substrate is attached to the skin around the stoma in the neck of the human subject, including, for example, a laryngectomy baseplate. Figure 3A ).exist Figure 2B In some embodiments, the first opening 100a seals, clips, or penetrates the stoma accessory opening 210, wherein the stoma accessory 200 may partially or deeply penetrate into the stoma, such as a laryngeal stoma button. Figure 3B Or a laryngostomy tube. In some embodiments, the first opening 100a seals, clips, or penetrates the stoma accessory opening 210, wherein the stoma accessory may be an exemplary tracheostomy tube widely used by tracheostomy users.

[0111] refer to Figure 2B In some embodiments, the speech generation system 100 uses an internal medical-grade barrier 105 as an interface to maintain a direct and hygienic connection with the stoma, wherein air exhaled from the stoma through a first opening 100a first passes through the medical-grade barrier before entering the rest of the speech generation system 100. In some embodiments, the speech generation system 100 uses an internal medical-grade barrier 105 as an interface to maintain a direct and hygienic connection with the stoma, wherein air inhaled from the stoma by the speech generation system 100 first passes through the medical-grade barrier before entering the stoma. Reference Figure 2B In some embodiments, the speech generation system 100 uses a medical-grade barrier 105 to maintain a direct and hygienic connection with the stoma accessory, wherein the medical-grade barrier 105 acts as a safe interface between the device and the stoma when the device is in direct contact with the airway, thereby maximizing its safety and hygiene. Reference Figure 2B In some embodiments, the speech generation system 100 uses a medical-grade barrier 105 to maintain a direct and hygienic connection with the stoma accessory, wherein the medical-grade barrier 105 functions similarly to an HME.

[0112] exist Figure 2BIn some embodiments, the medical-grade breathing barrier 105 is a detachable and removable part of the device. For example, the medical-grade breathing barrier 105 may be a disposable part of the device for everyday use. In some examples, the speech generation system 100 includes the medical-grade barrier 105, which is implemented as a permanent part of the device.

[0113] Figure 21-24 shows when... Figure 2B The preferred embodiment of the medical-grade respiratory barrier 105, implemented as part of the speech generation system, is a heat and moisture exchanger or an HME (HM100). In some examples, the HM100 includes a medical-grade foam (HM1001) that may be impregnated with a moisture-absorbing and heat-absorbing material to absorb moisture and keep the breathing air warm.

[0114] Figure 21 includes a variant of (HM100) in which the HME box (HM100) is located between the medical-grade stoma attachments 130 and is compatible with the different diameters of these stoma attachments 130.

[0115] Figure 22 shows an example of an HME box (HM100) as a detachable or included part of a device, wherein the box contains a barrier HM1002 that blocks or redirects sputum / phlegm that exits the stoma, for example due to coughing, so that the sputum / phlegm does not clog the HME foam HM1001 and breathing through the foam is not interrupted by sputum / phlegm contaminated by the foam.

[0116] Figure 23 An example of how the HME (HM100) can be customized for connection to the airflow chamber 100AC is shown. The airflow chamber can be designed to attach to or detach from a pre-existing medical-grade respiratory barrier. Alternatively, the device can be customized to connect to its compatible HME, as illustrated in this figure.

[0117] refer to Figure 2B In some embodiments, the speech generation system 100 disclosed herein may include a medical-grade barrier 105 (as part of a device) that is adjustable to accommodate the breathing capacity of different users, wherein the user's breathing capacity is measured using spirometry. For example, the density of the medical-grade barrier 105 may be quantified as follows: lower density for people with high breathing capacity and higher density for people with low breathing capacity, thereby making it easier for patients to breathe through the device, wherein the user's breathing capacity is measured using spirometry.

[0118] For interpretative purposes, a user's respiratory effort (also known as breathing capacity) corresponds to their expiratory performance, which can be assessed using standard methods, including expiratory volume assays, by measuring the pressure and flow rate of exhaled air. Expiratory volume assay parameters to be measured include the range of tidal and forced breathing pressures, which can be measured in kPa using pressure sensors suitable for monitoring tidal and forced breathing pressures (e.g., the NXP MPX series pressure sensors, which can measure respiratory pressures up to 4 kPa, 6 kPa, 10 kPa, or 15 kPa). Another important parameter for quantifying respiratory effort during vocalization is the peak respiratory flow rate (measured in liters per minute (LPM)) of the user's exhaled air from the stoma. This parameter can be measured using, for example, the Sensirion SDP series differential pressure sensors or the Sensirion SFM series flow meters. These sensors can measure the peak respiratory flow rate during vocalization in different subjects and can be calibrated to measure up to 6 L / min, 10 L / min, 15 L / min, or 20 L / min.

[0119] The voice generation system 100 can be customized to function for individuals whose tidal breathing level is 1.1 times, 1.2 times, 1.3 times, 1.4 times, 1.5 times, or the greater of their tidal breathing level, corresponding to a breathing effort (measured by breathing pressure or airflow).

[0120] refer to Figure 2B In some embodiments, the speech generation system 100 disclosed herein includes a medical-grade breathing barrier 105 (part of the device) that is adaptable to stoma accessory 200 substrates with different orifice sizes 210 and various stoma accessories, including, for example, adhesive or penetrating stoma accessories. This makes the device widely applicable to individuals with different stoma shapes, sizes, stoma locations, and skeletal structures.

[0121] refer to Figure 2C The speech generation system 100 also includes a medical-grade barrier 105 and an ostomy attachment 130 as part of the device. In some embodiments, the first opening 100a of the speech generation system 100 communicates with an ostomy using the ostomy attachment 130 connected to the medical-grade respiratory barrier 105, wherein the ostomy attachment 130 and the medical-grade respiratory barrier 105 are part of the device. In some embodiments, the ostomy attachment 130 may include an adhesive substrate, wherein the substrate is attached to the skin around the ostomy in the neck of a human subject. In some embodiments, the substrate 130 may include self-adhesive components, wherein the substrate is attached to the skin around the ostomy in the neck of a human subject, including, for example, a laryngectomy baseplate (or similar). Figure 3AIn some embodiments, the substrate 130 may be partially or deeply inserted into the stoma, for example, including or resembling a laryngostomy button. Figure 3B Or a laryngostomy tube. In some embodiments, the substrate may have an extension that partially penetrates the cervical stoma, such as a tracheostomy tube widely used by tracheostomy patients.

[0122] refer to Figure 2C In some embodiments, the first opening 100a communicates with the stoma, wherein the stoma is covered by a stoma attachment 130, which is configured to connect a device to the cervical stoma. Figure 2C In some embodiments, the stoma attachment 130 is a detachable part of the device. Figure 2C In some embodiments, the stoma accessory is a disposable part of the device for daily or longer-term use. The speech generation system 100 includes a medical-grade barrier 105, which is implemented as a permanent part of the device. (Reference) Figure 2C The voice generation system 100 includes a medical-grade barrier 105 and an ostomy accessory 130, which are implemented as disposable parts of the device after use.

[0123] refer to Figure 2C In some embodiments, the speech generation system 100 uses a medical-grade barrier 105 and a medical-grade stoma attachment 130, which are part of the device, to maintain a direct and hygienic connection with the stoma, wherein air exhaled from the stoma through the stoma attachment 130 reaches the first opening 100a and first passes through the medical-grade barrier 105 (part of the device) before entering the rest of the speech generation system 100. In some embodiments, the speech generation system 100 uses the stoma attachment 130 and the medical-grade barrier 105 as interfaces to maintain a direct and hygienic connection with the stoma, wherein air inhaled from the stoma through the speech generation system 100 first passes through the medical-grade barrier before entering the stoma.

[0124] refer to Figure 2C In some embodiments, the speech generation system 100 disclosed herein includes a medical-grade respiratory barrier 105 or an orifice size and shape of an ostomy accessory 130 adjustable to accommodate the breathing capacity of different users, wherein the user's breathing capacity is measured using a respiratory rate measurement method. For example, the shape of the medical-grade barrier 105 can be quantified to accommodate individuals with low, moderate, or high breathing capacities, wherein the user's breathing capacity is measured using a respiratory rate measurement method. In some embodiments, the speech generation system 100 disclosed herein includes a first opening 100a that is adjustable to accommodate ostomy accessory 130 substrates with different orifice sizes 210 and various ostomy accessories, including, for example, adhesive or penetrating ostomy accessories. This makes the device widely applicable to individuals with different ostomy shapes, sizes, ostomy locations, and skeletal structures.

[0125] For interpretative purposes, a user's respiratory effort (also known as respiratory capacity) corresponds to their expiratory performance, which can be assessed using standard methods, including respiratory volume measurement, by measuring exhaled air pressure and airflow. Parameters to be measured include the range of respiratory pressures, which can be measured in kPa, using pressure sensors suitable for respiratory body pressure monitoring (e.g., the NXP MPX series pressure sensors, which can measure respiratory pressures up to 4 kPa, 6 kPa, 10 kPa, or 15 kPa). Another important parameter for quantifying respiratory effort during vocalization is the peak respiratory airflow (measured in liters per minute (LPM)) exhaled from the stoma. This parameter can be measured using, for example, the Sensirion SDP series differential pressure sensors or the Sensirion SFM series flow meters, which can measure peak respiratory airflows during vocalization in different subjects, up to 6 L / min, 10 L / min, 15 L / min, or 20 L / min.

[0126] The effort exerted during phonation is typically less than a person's peak respiratory airflow / pressure and closer to the value corresponding to tidal breathing. The speech generation system 100 is customized to function for individuals whose tidal breathing level is 1.1 times, 1.2 times, 1.3 times, 1.4 times, 1.5 times, or a larger value compared to their tidal breathing level, corresponding to a respiratory effort (measured by respiratory pressure or airflow).

[0127] airflow chamber In some embodiments, the speech generation system 100 disclosed herein may include an airflow cavity 100AC. Reference Figure 4A In some embodiments, the airflow cavity 100AC disclosed herein may include a first opening 100a (air inlet / outlet) communicating with the subject's stoma or stoma accessory 200. In some embodiments, the housing 100AC disclosed herein may include a second opening 100b (air inlet / outlet) communicating with open air. In some embodiments, the airflow cavity includes a third opening 100AC_c (air outlet) communicating with the speaker cavity 100VC. In some embodiments, the airflow cavity includes a fourth opening communicating with open air. In some embodiments, the airflow cavity includes a fourth opening 100AC_d (air window) communicating with open air using a movable window. In some embodiments, the airflow cavity includes more than four openings.

[0128] In such Figure 4BIn some exemplary embodiments shown, the airflow cavity includes a housing enclosure 1000_AC, which includes a first opening 100a and a third opening 100AC_c, and a breathable surface 1000_AC_b forming a second opening 100b. In some exemplary embodiments, the airflow cavity includes the housing enclosure 1000_AC and the breathable surface 1000_AC_b, wherein the housing 1000_AC forms an air passage including a first opening (air inlet / outlet) 100a and a second opening 100b, a third opening 100AC_c (air outlet) or more openings through the breathable surface 1000_AC_b.

[0129] In some embodiments, the airflow cavity 100AC disclosed herein is in communication with an ostomy attachment 200, such as an adhesive or penetrating ostomy attachment 200 that is not part of the device. In some embodiments, the airflow cavity 100AC is in communication with an ostomy attachment 130 that is part of the device. Figure 2C (Connected). In some embodiments, the airflow chamber may be cleaned and / or disposable after use to maximize its hygiene. In some embodiments, the airflow chamber 100AC may be discarded after a set period of time (from one day to several months).

[0130] In some embodiments, the first opening 100a of the airflow cavity is connected to the stoma accessory substrate using a medical-grade respiratory barrier. In some embodiments, the first opening 100a of the airflow cavity 100AC may include a connector. In some embodiments, the airflow cavity connector may be coupled to the medical-grade barrier, wherein the medical-grade barrier acts as an interface between the stoma accessory and the airflow cavity, and the airflow cavity does not directly contact the stoma. In some embodiments, the medical-grade barrier is implemented inside the airflow cavity, wherein the airflow cavity partially penetrates the connection port of the stoma accessory and can directly contact the stoma.

[0131] In some embodiments, the first opening 100a of the airflow cavity is attached to a medical-grade respiratory barrier. Referring to FIG5, the medical-grade respiratory barrier 105 or 205 is connected to the stoma accessory opening 210. In some embodiments, the medical-grade respiratory barrier 105 or 205 may be attached to or detached from the first opening 100a. In some embodiments, such as Figure 2A As shown, the medical-grade respiratory barrier 205 is not part of the airflow chamber. In some embodiments, such as Figure 2B As shown in 2C, the medical-grade respiratory barrier 105 is part of an airflow chamber. In some embodiments, the medical-grade respiratory barrier device may be a heat and moisture exchanger (HME).

[0132] Referring to the embodiment in Figure 5, an example of an airflow cavity is shown, where the HME is, for example, an HME disc 205, which is detachable and not part of the device. The HME is attached to or detached from the first opening 100a of the airflow cavity and can be discarded daily, allowing for longer-term use of the airflow cavity. In this embodiment, the airflow cavity does not enter the stoma accessory and is connected to the stoma accessory via the HME as an interface. In this embodiment, the airflow cavity does not directly contact the stoma.

[0133] In some embodiments, such as Figure 6A As shown, the medical-grade respiratory barrier is implemented as an inseparable part of the airflow chamber 100AC, wherein the airflow chamber and its contained medical-grade respiratory barrier 105 are used as a unit. In some embodiments, the airflow chamber 100AC and its inseparable medical-grade respiratory barrier 105 can be discarded daily to maximize hygiene. In this embodiment, the portion of the airflow chamber 100AC and its contained medical-grade respiratory barrier 105 enters the stoma accessory and comes into direct contact with the air exiting the airway through the stoma.

[0134] In some embodiments, such as Figure 6B As shown, the medical-grade respiratory barrier (105) is detachable but placed within a reusable airflow chamber 100AC, wherein the airflow chamber can be opened to add or remove the medical-grade respiratory barrier (105), wherein the airflow chamber can be used and cleaned for more than one day, and the medical-grade respiratory barrier 105 is detachable and can be discarded over a shorter period of time (e.g., daily). In some embodiments, such as... Figure 6B As shown, the medical-grade respiratory barrier is detachable, but it is part of the device, wherein the airflow chamber housing can be opened to include the medical-grade respiratory barrier and is discarded daily after use. In such an embodiment, the medical-grade respiratory barrier 105 is used daily, while the airflow chamber 100AC can be used for a longer period. In this embodiment, the airflow chamber 100AC and its included portion of the medical-grade respiratory barrier 105 enter the stoma accessory and come into direct contact with the air exiting the airway through the stoma.

[0135] In some embodiments, the medical-grade respiratory barrier (205) is detachable and not part of the airflow chamber (100AC), wherein the medical-grade respiratory barrier 205 may be discarded for a short period of time (e.g., daily), while the airflow chamber 100AC may be used for a longer period of time. In some embodiments, the medical-grade respiratory barrier 205 is detachable but not part of the device, but the device housing may be opened to include the medical-grade respiratory barrier 205, such as an HME, and discarded after a short period of use (e.g., daily). In such embodiments, the medical-grade respiratory barrier is used for a shorter period of time, such as daily, while the airflow chamber may be used for a longer period of time.

[0136] In some embodiments, the airflow chamber 100AC communicates with a patient's cervical stoma and receives inhaled and exhaled airflow from the stoma. In some embodiments, the airflow chamber disclosed herein may include at least a three-way or four-way valve, wherein at least three or four different usage modes include: automatic inhalation and automatic exhalation (bidirectional breathing), whereby the user can inhale and exhale naturally without removing the device from the stoma or stoma accessory 200; voice generation when the user exhales more as an indication of voice onset than tidal breathing; and a fourth bypass mode in which the user can disable the device when the user needs to cough or breathe forcefully without removing the device from the stoma accessory; in some embodiments, the airflow chamber 100AC disclosed herein includes a multi-way valve capable of providing more usage modes.

[0137] In some embodiments, the airflow chamber 100AC further includes a movable gas element 120 located within the housing 1000AC and configured to prevent, facilitate, or redirect airflow within the airflow chamber through some or all of the airflow chamber openings or between some or all of the airflow chamber openings in different usage modes. In some examples, the movable gas element 120 is located within the airflow chamber 100AC. In some examples, the movable gas element 120 extends laterally through the airflow chamber 100AC in a direction perpendicular to the airflow between the first opening 100a and the second opening 100b within the airflow chamber. In some embodiments, the disclosed airflow chamber is a pressure- or airflow-activated movable gas element that automatically switches between some or all usage modes, including, for example, a bidirectional breathing, voice generation, or bypass mode of the device.

[0138] In some embodiments, the breathing pattern includes the subject's natural tidal exhalation, in which air is exhaled through the stoma and through a medical-grade respiratory barrier to a first opening 100a of the airflow chamber 100AC, wherein the exhaled air passes through the airflow chamber and exits through a second opening 100b of the airflow chamber. In some embodiments, the movable air element 120 can achieve an automatic exhalation pattern by allowing the air passage from the first opening 100a to exit through the second opening 100b without removing the airflow chamber 100AC from the stoma or stoma accessory 200. In some embodiments, the breathing inhalation pattern includes the subject's natural tidal inhalation, wherein inhaled air enters the airflow chamber 100AC through the second opening 100b, passes through the airflow chamber, and exits through the first opening 100a to move toward the stoma. The inhaled air then moves toward the stoma after passing through a medical-grade respiratory barrier 105 or 205. In some embodiments, the movable member 120 can achieve an automatic inhalation mode by allowing or facilitating an air passage from the second opening 100b to the first opening 100a without removing the airflow chamber 100AC from the stoma or stoma accessory 200.

[0139] In some embodiments, when the air intake chamber is in communication with the user's stoma, the movable air element 120 is in a default breathing mode (inhalation / exhalation), allowing the patient to breathe freely between the first and second openings without removing the airflow chamber 100AC from the stoma or stoma accessory 200. In some embodiments, the third opening (exit port) 100AC_c of the chamber is connected to a speech generation chamber, which has a higher aerodynamic resistance path compared to the second opening 100b (which is connected to open air). Therefore, as long as the movable element allows air to exit from the second opening 100b in the default breathing mode (inhalation / exhalation), air will not exit from the outlet port 100AC_c, thus keeping the speech chamber disabled.

[0140] In some embodiments, the speech generation mode includes the subject exhaling air normally from the lungs with a higher airflow than tidal exhalation, serving as an indication of the start of speech. In some embodiments, when the subject exhales a higher airflow through a stoma, through a medical-grade respiratory barrier 105 or 205 to a first opening 100a of the airflow chamber, wherein the exhaled air has a higher magnitude than tidal exhalation, the movable air element 120 responds to the higher airflow and closes the second opening 100b of the chamber. In the speech generation mode, exhaled air flows from a third opening 100AC_c to a speech cavity 100VC, which generates speech in response to the exhaled airflow.

[0141] In some embodiments, the movable gas element 120 may be made of a flexible or thin plastic material; in some embodiments, the movable gas element 120 may be made of a flexible silicone material. In some embodiments, the movable gas element 120 may be made of an electronically operated airflow or pressure-activated electronic switch, which may be implemented, for example, by a voice coil actuator.

[0142] In some examples, the movable gas element 110 contained within the airflow cavity is made of a flexible membrane (also known as an air film). In some exemplary embodiments, the air film 110 may be placed within the airflow cavity housing 1000_AC, such that the passage of inhaled or exhaled air within the cavity causes the membrane to move, thereby closing, restricting, or opening the airflow cavity opening. In some exemplary embodiments, such as Figure 7A As shown, the air film 110 can be a circular disk made of flexible silicone material. In some exemplary embodiments, the air film 110 is placed inside the airflow cavity housing 1000_AC and fixed to the air-permeable surface 1000_AC_b. In some exemplary embodiments, such as Figure 7B As shown, the air membrane is fixed on the breathable surface 1000_AC_b and its inner side against the anchor point 1000_AC_an. Figure 7AAn example of a membrane as a flexible circular disk is shown, which is positioned around the air-permeable surface 1000_AC_b inside and on anchor points of the airflow cavity for easy membrane replacement when needed. (Including...) Figure 7B In some embodiments, the breathable surface 1000_AC_b can be attached to or detached from the airflow cavity for easy membrane replacement. In some embodiments, the air membrane 110 can be attached to or detached from the airflow cavity and is disposable after use. In some embodiments, the membrane is fixed to the disposable breathable surface 1000_AC_b, wherein the membrane and the breathable surface 1000_AC_b can be used together and then disposed of. In some embodiments, the airflow cavity is disposable and replicable. In some embodiments, the air membrane 110 is washable and reproducible.

[0143] In some examples, such as Figure 8A and 8B As shown, the air membrane 110 is fixed on the breathable surface 1000_AC_b and inside the anchor point 1000_AC_an, and is aligned with the direction of air from the second opening 100b. When the user inhales or exhales, the default position of the air membrane bends inward to keep the breathable surface of the second opening 100b open, allowing for free bidirectional tidal breathing. Figure 8B In some examples, the membrane is anchored to a point on the second opening, wherein when the exhaled airflow has a greater magnitude than the tidal exhalation, the air membrane 110 is pushed to close the permeable surface 1000_AC_b of the second opening 100b. Figure 8A This redirects air to the third opening 100AC_c, and then to the speech generation cavity 100VC, enabling the device to generate speech for the patient.

[0144] In some embodiments, the air membrane 110 of the airflow chamber 100AC can be adjusted and customized within a range of materials. In some embodiments, the membrane of the airflow chamber may include natural rubber or medical-grade silicone. In some embodiments, the air membrane 110 is composed of a thin silicone membrane, which may be flexible to respond to respiratory movement. In some embodiments, the membrane of the airflow chamber can be quantified within a range of thicknesses. In some embodiments, the membrane of the airflow chamber has a thickness of 0.05 mm to 0.5 mm. In some embodiments, the membrane of the airflow chamber can be quantified within a range of flexibility (e.g., hardness ranging from Shore A10 to 60). In some embodiments, the membrane is made of a harder or thicker plastic or metallic material.

[0145] In some embodiments, the airflow cavity or air membrane 110 can be quantified within a range of different shapes, materials, flexibility, or thicknesses to match a wide range of breathing capacities in different individuals. In some embodiments, the membrane of the airflow cavity can be quantified within the range of a subject's breathing capacity, wherein the subject's breathing capacity is measured by a respiratory rate measurement method. In some embodiments, the subject's breathing capacity is measured by an airflow meter connected to the airflow cavity 100AC, by measuring the peak exhaled airflow (liters / minute) of tidal breathing to estimate the threshold for the onset of speech generation. The air membrane 110 can be customized to activate the outlet 100AC_c of the speech cavity, thereby enabling the device to generate speech for a person with a comfortable breathing effort (measured by tidal breathing pressure or peak respiratory airflow), which corresponds to 1.1 times, 1.2 times, 1.3 times, 1.4 times, 1.5 times, or a value greater than the person's tidal breathing level.

[0146] In some embodiments, the membrane of the airflow cavity is adjusted to initiate movement of the air membrane 110 as the respiratory airflow increases from tidal breathing to the onset of speech. In some embodiments, the thickness, shape, or material of the air membrane 110 of the airflow cavity can be quantified for low, medium, or high respiratory capacities based on a patient's measured tidal breathing level compared to the average tidal breathing airflow (6 liters / minute). In some exemplary embodiments, the thickness of the airflow cavity membrane is quantified from 0.1-0.3 mm (Shore A flexibility 20-50) for low respiratory capacities, 0.2-0.4 mm (Shore A flexibility 20-50) for medium respiratory capacities, or 0.3-0.5 mm (Shore A flexibility 20-50) for high respiratory capacities, so that more respiratory energy can be used for movement for individuals with higher respiratory capacities than average. In some embodiments, the shape of the air membrane 110 and the airflow cavity anchor point 1000_AC_an can be quantified for small, medium, or large respiratory capacities to make the membrane easier to move for lower respiratory capacities.

[0147] In some embodiments, the airflow cavity 100AC includes a movable air element 110, which is controlled or assisted by a finger-touch mechanism to switch between a breathing mode and a voice generation mode. In some embodiments, the finger-touch mechanism is mechanical, for example, a spring element placed within the air cavity and connected to an anchor point 100_AC_b within the breathable surface 1000_AC_b (e.g., as shown in the image). Figure 7A As shown in the diagram, the user presses inward on the breathable surface 1000_AC_b to close the second opening 100b and directs exhaled air out through the air outlet 100AC_c, thereby manually controlling the voice generation mode. When the finger pressure is removed, the second opening 100b returns to its default bidirectional breathing position.

[0148] In some embodiments, the finger touch mechanism is an electronic touch sensor that toggles the on / off state of the device's voice generation mode when a user briefly touches the sensor surface. In some embodiments, the touch sensor switches between the device's voice generation mode and breathing mode. In some embodiments, the touch sensor is located on the airflow chamber 100AC housing or other parts of the device and communicates with the movable air element 110 via a wired connection. In some embodiments, the touch sensor is located on the speaker chamber or other parts of the device and communicates with the movable air element 110 via a Bluetooth® connection. In some embodiments, the touch sensor initiates the start of the voice generation mode, and when the breathing pressure drops below a voice stop threshold, a pressure activation switch initiates voice stop to return the device to bidirectional breathing. In some embodiments, the pressure activation switch for restoring the device to the default breathing mode may be the movable air element 110.

[0149] exist Figure 4A In some embodiments, the airflow cavity 100VC disclosed herein has a bypass mode, wherein the bypass mode is provided by a movable window 100AC_d in communication with open air. In some exemplary embodiments, the airflow cavity disclosed herein may include a movable window, wherein the movable window 100AC_d can be manually opened to bypass the second opening 200a and the speech generation cavity, and to allow free bidirectional breathing through the window 100AC_d, including coughing or forceful exhalation. In some embodiments, the airflow cavity disclosed herein may include a window, wherein when the window is closed, the speech generation system 100 maintains a standard bidirectional and speech generation mode. In some embodiments, the airflow cavity disclosed herein may include a window, wherein a user can open the window to bypass the device and allow free breathing when experiencing pain or discomfort. In some embodiments, the airflow cavity disclosed herein may include a window, wherein a user can open the window such that excessive exhalation (e.g., coughing or forceful breathing) does not engage the speech generation cavity.

[0150] exist Figure 4B In some exemplary embodiments, the movable window 100AC_d can be implemented on the housing 1000_AC within the airflow cavity. In some exemplary embodiments, the movable window can be implemented on the ventilated surface 1000_AC_b, or on a combination of the housing 1000_AC and the ventilated surface 1000_AC_b. Figure 4B The airflow cavity housing 1000_AC may include a window 1000_AC_wl, and the ventilated surface 1000_AC_b may have a movable wall 1000_AC_wl, which can rotate about its axis within the housing 1000_AC, thereby opening or closing the window 1000_AC_wl.

[0151] In some embodiments, the movable window may be implemented, for example, on the breathable surface 1000_AC_b, without requiring a fourth opening. In some embodiments, the breathable surface 1000_AC_b may be rotatable, for example, by a threaded mechanism within the airflow chamber housing 1000_AC, and may have a movable attachment that moves within the breathable surface 1000_AC_b and increases the distance between the membrane 1010 and the breathable surface 100AC_b, thereby increasing the distance between the membrane 1010 and the breathable surface 100AC_b, thereby allowing air to escape from the breathable surface 1000_AC_b and holding the movable member in a permanently open position to keep the second opening 100b open and bypass the air outlet 1000_AC_c. In some embodiments, the fourth opening may be embedded in the breathable surface 1000_AC_b by other mechanisms, for example, by rotating the breathable surface 1000_AC_b to increase its air outlet mesh size to become larger than the movable air member 110, thereby allowing air to escape freely in bypass mode without engaging the movable air member 110.

[0152] In some embodiments, the airflow chamber 100AC includes a movable window actuated by a finger-touch mechanism to switch between bypass mode and voice / breathing mode. In some embodiments, the finger-touch mechanism is mechanical, for example, by placing a spring element within the airflow chamber connected to a preferably disc-shaped ventilated surface 1000_AC_b, wherein the user releases the ventilated surface 1000_AC_b outward to lock the air gap between the airflow chamber housing 1000AC and the second opening 100b, thus acting as an open window to facilitate breathing (bypass mode) and to guide inhaled / exhaled air, as well as strong airflow / coughing, into and out of the air gap in the second opening 100b. By pushing the ventilated surface 1000_AC_b inward with finger-touch force to lock the second opening 100b in a default position, the air gap is closed, and the second opening 100b returns to its default position in the bidirectional breathing / voice mode.

[0153] In some embodiments, attaching or detaching the airflow cavity (including its connection to a medical-grade respiratory barrier) to or from the stoma accessory 200 can expose the patient's stoma and create a biosafety risk of an unprotected stoma. In some embodiments, as shown in FIG9, the airflow cavity 100AC includes: (i) a stable housing 9000_A ( Figure 9A The stable housing is retained on the stoma accessory 200 to always protect the stoma, wherein the stable housing includes a first opening 100a communicating with the stoma and a second opening communicating with open air through a breathable (mesh) surface (9000_A_b). The stable housing (9000_A) may also include a medical-grade barrier (105 or 205) to communicate with the inhaled / exhaled airflow of the stoma. Figure 9BIn some embodiments shown, the airflow chamber 100AC further includes (ii) a detachable housing (9000_B) that is attached to or detached from the stabilizer when the patient intends to use or discontinue using the device, and can function as a similar to Figure 4A A multi-mode air valve depicting the structure of an airflow chamber. In some embodiments, the detachable housing (9000_B) includes a first opening attached to the stable housing (9000_A), for example by clipping onto a breathable surface (9000_A_b), wherein air from the stoma or exhaled air passes through the breathable (mesh) surface (9000_A_b) through the stable housing (9000_A) and enters the detachable housing (9000_B). The detachable housing may also include a second (900_B_b), a movable member 110, and a third opening 100AC_c, similar to... Figure 4A The illustrated embodiments. In some embodiments, the air cavity has a stable and detachable housing structure ( Figure 9C This provides maximum portability for the device and facilitates continuous use. In some embodiments, the dual-shell airflow chamber can be used as a standard HME to maximize stoma safety and facilitate continuous use.

[0154] In some embodiments, the voice generation system 100 can provide portability, wherein the air outlet 100AC_c of the airflow chamber 100AC is via a detachable connection. In some embodiments, such as Figure 10 As shown, the air outlet 100AC_c can be detached, for example, by a magnetically detachable connector to maintain the portability of the device. In some embodiments, the airflow chamber housing 1000_AC has a magnetic connection to the air outlet 100AC_c, wherein the detachable outlet tube 11010 can be attached to or detached from the housing using, for example, a magnetic attachment / detachment. In some embodiments, the magnetically detachable air outlet 100AC_c of the airflow chamber allows the speech chamber 100VC and other parts of the device to be removed and placed in a carrying case when speech generation is not required, thereby maximizing portability. In some embodiments, when the air outlet 100AC_c of the airflow chamber is detached, the airflow chamber can remain connected to the medical-grade respiratory barrier 105 or 205 and communicate with the stoma accessory, thereby serving as a standard HME to protect the stoma.

[0155] In some embodiments, the passage of naturally moisture-containing exhaled airflow through the airflow chamber 100AC may occasionally cause condensation to build up inside the device. In some embodiments, the airflow chamber 100AC may include a moisture trap (also referred to as a water trap) to capture and contain condensed water droplets inside. In some embodiments, the moisture trap may redirect condensed water droplets present within the airflow chamber housing 1000_AC from proceeding to the movable member 110 or toward the stoma via the first opening 100a. In some embodiments, the water trap may restrict and redirect fluid including saliva traveling from the outlet 100AC_c toward the airflow chamber 100AC from reaching the stoma.

[0156] In some embodiments, such as Figure 11 As shown, the water trap 100_AC_WT is part of the airflow cavity 1000_AC, wherein small water droplets move out of the airflow cavity 1000_AC through a one-way water trap opening 10010, which guides the small water droplets formed inside the airflow cavity 100_AC into the water trap in the direction of gravity. In some embodiments, such as Figure 11 As shown, the water trap includes a water reservoir 10030, into which small water droplets are added for removal when needed. In some embodiments, such as Figure 11 As shown, the water trap includes an outlet valve 10020, which includes a movable rubber that opens to allow droplets to drain from the device. In some embodiments, the outlet valve 10020 is made of openable flexible rubber, allowing fluid collected in the water trap to be released and the water trap to be reused. In some embodiments, such as Figure 11 As shown, the water trap 100_AC_WT is connected to and is part of the air outlet 100AC_c of the airflow chamber, wherein air exiting the air outlet 100AC_c helps remove small water droplets from the device to the water trap. In some embodiments, the water trap has a touch sensor or a mechanical outlet 10020 connected to a spring to release water from the device.

[0157] In some embodiments, the airflow cavity disclosed herein may include a humidity detector or sensor. In some embodiments, the humidity detector is in communication with the airflow cavity 100AC. In some embodiments, the humidity detector may alert a subject to the presence of potential moisture, condensation, saliva, or small water droplets in the airflow cavity, wherein the humidity detector alerts the subject when it detects moisture. In some embodiments, the humidity detector's alert includes, for example, a visual indicator (e.g., a change in the color of a section of the airflow cavity), an indicator light, or an audible signal. In some embodiments, the moisture trap has a touch, mechanical, or electromechanical outlet connected to a spring to release moisture when the humidity sensor alerts the user to accumulated humidity inside the device.

[0158] airflow duct The speech generation system 100 also includes and is limited to, for example, Figure 2A-2C The air passage, air channel, or airflow duct 133 is described in a general embodiment. (See reference...) Figure 12A and 12B In some embodiments, the airflow chamber 100AC is connected to the airflow duct 133. In some embodiments, the airflow duct 133 disclosed herein includes a first opening 1331 and a second opening 1332. In some embodiments, the first opening of the airflow duct 133 is connected to a third opening (air outlet) of the airflow chamber 100AC_c. In some embodiments, the second opening of the airflow duct 1332 is connected to the speaker cavity 100VC. In some embodiments, the airflow duct 133 is an airflow pipe (also known as a flow tube).

[0159] In some embodiments, the flow tube 133 includes a flexible tube. In some embodiments, the flow tube is made of a rigid tube. In some embodiments, the flow tube includes a medical-grade biocompatible tube. In some embodiments, the flow tube is disposable after use to maximize device hygiene. In some embodiments, the flow tube is also disposable for daily use or for longer use to maximize device hygiene. In some embodiments, the length of the flow tube is adjustable and can be extended to match the neck length of different subjects.

[0160] In some embodiments, as shown, the flow tube 133 may be attached to or detached from the airflow cavity or voice cavity to maximize device portability. In some embodiments, as shown, the flow tube 133 may be attached to or detached from the airflow cavity or voice cavity to maximize device safety, wherein the airflow cavity 100AC and the medical-grade barrier 105 or 205 remain on the stoma, while the flow tube 133 and the voice cavity 100VC can be carried in a portable case for use when needed. In some embodiments, as shown, the flow tube 133 may be attached to or detached from the airflow cavity or voice cavity via a mechanical connection. In some embodiments, as shown, the flow tube 133 may be attached to or detached from the airflow cavity or voice cavity via a magnetic connection, wherein the tube openings 1331, 1332 are, for example, embedded with a magnetic ring that connects to or disconnects from the openings in the airflow cavity and voice cavity.

[0161] In some embodiments, such as Figure 13As shown, the flow tube 133 is designed to provide a hands-free function and eliminate the need for the user to manually hold the device. In some embodiments, the flow tube 133 is a flexible tube with springs or wire frames embedded around or inside the tube wall to spring back to its original position, thereby enabling hands-free use of the device. In some embodiments, the flow tube 133 is a rigid tube made of rigid medical-grade silicone with a rigidity of, for example, Shore A 50 or higher, which maintains its shape to keep the voice source in place, thereby enabling hands-free use of the device. In some embodiments, the flow tube 133 is a flexible tube with a bending radius greater than 90 degrees to avoid tube blockage of airflow.

[0162] In some embodiments, exhaled airflow naturally containing moisture occasionally causes condensation inside the flow tube as it passes through the flow tube. In some embodiments, saliva droplets seep from the speech cavity 100VC toward the flow tube, causing saliva droplets to leak into the tube. In some embodiments, the wall of the flow tube 133 may have a movable window that rotates about the tube axis to allow exhaled air to exit through the window and reduce the condensation effect. In some embodiments, the flow tube has a water trap that captures and retains condensed droplets to prevent them from reaching the flow cavity. In some embodiments, the inner surface of the flow tube may be modified (e.g., microgrooves embedded in the inner wall of the tube) to guide condensation or saliva droplets within the tube toward the water trap within the flow tube. In some embodiments, the water trap of the flow tube may be implemented, for example, as a double-walled tube with porous boundaries or micropores (e.g., 0.5-1 mm in diameter) between the two layers, wherein air passes through the inner tube while condensed droplets accumulated on the inner wall seep into the micropores and are captured in the outer tube.

[0163] In some embodiments, the airflow duct 133 or other portions of the device may be made of a selectively semi-permeable material that diverts water vapor, condensation, or accumulated moisture to the environment, thereby reducing or preventing condensation, while simultaneously preventing air from escaping from the device. In some embodiments, the duct 133 is made of a highly selectively semi-permeable material that allows moisture accumulated inside the duct to pass through and be diverted to the outside of the duct wall, while retaining air inside. In some embodiments, these selective materials may provide such semi-permeability based on the vapor pressure difference between the inside and outside of the device.

[0164] In some embodiments, the inner surface of the flow tube 133 may be covered with a moisture-proof material. In some embodiments, the moisture-proof material prevents condensation or saliva from forming droplets inside the tube. In some embodiments, the moisture-proof material may comprise a hydrophobic or superhydrophobic coating. In some embodiments, the hydrophobic or superhydrophobic coating includes a coating such as Aqualene® 5000: a high-performance OGR coating. In some embodiments, the moisture-proof material comprises a biosafe or biocompatible hydrophobic polymer.

[0165] In some embodiments, the flow tube 133 may have a condensation wiping mechanism, for example, using a movable magnetic ring attached to the surface of the inner flow tube 133 wall, which is coupled to a movable magnetic ring outside the tube, wherein the outer and inner magnetic rings are magnetically coupled to each other, and moving the outer ring causes the inner ring to move, thereby wiping the condensed water downward from the inside of the flow tube toward the water trap.

[0166] Because moisture condenses inside the tube, condensation occurs more frequently in cold or more humid weather. In some embodiments, the tube 133 can be thermally insulated to prevent exhaled moisture from condensing into droplets inside the tube. In some embodiments, thermal insulation within the tube involves, for example, using a heating copper coil implemented within the tube wall. In some embodiments, the heating copper coil integrates a battery-powered current source. This current source generates current flowing through the heating copper coil, thermally insulating the tube wall from cold weather and thus preventing condensation. In some embodiments, the user can initiate thermal insulation using a manual electronic switch.

[0167] In some embodiments, the flow tube may include a temperature sensor and a battery. The temperature sensor is used to monitor the temperature inside or around the flow tube. When the sensor detects a low external temperature that would cause condensation, it activates a battery-powered current source to initiate a heating process. In some cases, the battery-powered current source may include a standard battery, or in others, a rechargeable battery.

[0168] In some embodiments, the flow tube 133 may use an external coating for insulation. This insulation typically involves foam insulation or a polymer coating. In such cases, the outer surface of the flow tube is surrounded by foam insulation, and the component is further protected by a polymer coating. The specific materials used in the foam insulation and polymer coating can vary. In some cases, the foam insulation may include a polymer coating comprising medical-grade polystyrene or polyurethane foam.

[0169] Voicebox chamber In some embodiments, the present invention may include, for example, Figure 2A-2C The speaker cavity 100VC is described in a general embodiment. In some embodiments, the invention may include a speaker cavity 100VC that converts exhaled airflow into speech (sound waveform), which can be used by a person with a missing or damaged larynx to produce sound. In some embodiments, the invention may include a speaker cavity in which the speaker cavity converts respiratory airflow into extremely high-quality speech. In some embodiments, the speaker cavity generates sound that can be modulated by mouth movements of a person with a missing or damaged larynx, thereby generating an extremely high-quality vocal signal.

[0170] In some embodiments, such as Figure 14As shown, the speaker cavity 100VC disclosed herein may include a housing 1000VC having a first opening 100VC_a and a second opening 100c, wherein the first opening 100VC_a communicates with a flow tube 133 and receives exhaled airflow from the stoma exiting the flow tube. In some embodiments, the speaker cavity housing 100VC has a second opening (open-mouth speech outlet) 100c that communicates with a user's oral cavity. In some embodiments, the speaker cavity housing 100VC has a second opening (open-mouth speech outlet) 100c that communicates with an oral cavity adapter 100d. In some embodiments, breathing or air enters the first opening 100VC_a of the speech cavity 100VC, and the resulting speech and exhaled airflow exit the second opening 100c to the oral cavity adapter 100d and reach the user's mouth, wherein the speech and airflow excite the vocal tract, enabling the patient to produce sound. In some embodiments, the speaker cavity 100VC may have more than two openings. In some embodiments, the speaker cavity 100VC is a disposable unit.

[0171] In some embodiments, such as Figure 2A-2C As described in a general embodiment, the speaker enclosure 100VC may include a movable voice member 120. In some embodiments, the movable voice member 120 may reside within the speaker enclosure. In some embodiments, such as Figure 14 As shown, the movable speech component can generate sound in response to breathed air passing through the speaker cavity from the first opening 100VC_a, whereby the sound exits the speaker cavity through the second opening 100c. In some embodiments, speech generation of the movable speech component 120 can be driven by exhalation, thereby generating high-quality speech.

[0172] In some embodiments, the speech generation system and method 100 utilizes the functionality of the movable air element 110 and the movable speech component 120 to automatically control the start and end of speech using the patient's breathing, and generates extremely high-quality speech. In some embodiments, the speech generation system and method 100 utilizes the interaction between the movable air element 110 and the movable speech component 120 to automatically control the start and end of speech and the voiceless / voiced transition during phonation.

[0173] In some embodiments, such as Figure 2A-2CAs shown, at the start of speech, exhaled airflow exits from the stoma and enters the airflow chamber, where a movable air element is engaged to guide the airflow through the flow tube 133 to the speech cavity 100VC. This airflow causes the movable speech member 120 to vibrate and generate speech. In some embodiments, at the end of speech, the exhaled airflow decreases, and the movable air element 110 returns to its default position, directing the exhaled airflow to the open inlet / outlet 100b, which prevents the airflow from reaching the speech cavity and the movable speech member 120, and stops speech generation. In some embodiments, the movable air element 110 is responsible for controlling automatic speech start and end control, while the movable speech member 120 is responsible for generating speech based on breathing. In some embodiments, the interaction between the movable air element 110 and the movable speech member 120 affects the automatic speech start and end control.

[0174] In some exemplary embodiments, the movable member 120 may include medical-grade silicone. In some embodiments, the voice diaphragm 120 may include a thin film of natural or synthetic rubber, metal, or other vibrating material. In some examples, the movable voice member may include a double-layered, thin, hollow silicone membrane filled with a gel material, such as PEG (polyethylene glycol) hydrogel widely used for in vitro vocal cord simulation, or fluid injection, either entirely or in specific portions, between the two layers to simulate the fluid-based structure of the human vocal cords. In some embodiments, the movable member may include a silicone sheet with patterns printed or extruded on its surface to simulate the irregular structure of vocal cord vibration.

[0175] In some embodiments, the movable speech member 120 disclosed herein may include a speech diaphragm 120. In some embodiments, the speech diaphragm 110 disclosed herein may be placed within a speech cavity 100C, near the second opening 100c, and align with the direction of airflow through the speech cavity 100C. In some embodiments, the speech diaphragm may vibrate in response to airflow through the speech cavity and out of the second opening 100c, thereby generating speech. In some embodiments, the speech diaphragm may be easily inserted into or removed from the speech cavity 100C without interfering with other parts of the device, and is disposable after use.

[0176] In some embodiments, the voice diaphragm is made of a flexible sheet (e.g., 0.1 to 0.5 mm thick) of, for example, natural or synthetic rubber or silicone, which is flexible (e.g., Shore A stiffness of 20-50) to vibrate in response to exhaled airflow. In some embodiments, the voice diaphragm is made of a flexible sheet of, for example, natural or synthetic rubber or silicone, whose inherent resonant frequency is within the fundamental frequency range of human voice (which can vary from 70 Hz to above 300 Hz). In some embodiments, the voice diaphragm can be customized with a range of thickness and flexibility to create sound for people with different breathing capacity levels. In some embodiments, the voice diaphragm 120 can be quantized on parameters such as flexibility or thickness to create sound for people with different breathing capacity levels. Furthermore, the voice diaphragm can be quantified to accommodate subjects with low, medium, or high airflow capacity. In some embodiments, the voice diaphragm can be quantified on parameters such as flexibility or thickness such that the vibrational initiation of speech is matched to the user's breathing effort, thereby relating the speech generation initiation to the user's minimum breathing effort closer to tidal breathing to avoid long-term fatigue.

[0177] Figure 15 A preferred embodiment of the speech generation system 100 is shown. In some embodiments, at the onset of speech, exhaled airflow exits from the stoma and reaches a first opening of the airflow chamber 100a, where an air membrane 110 closes a second opening 100b, directing the airflow to a third opening 100_AC_c and reaching the flow tube. Air through the flow tube 133 reaches the speech cavity 100VC and can cause the speech diaphragm 120 to vibrate to generate speech. In some embodiments, at the end of speech, exhaled airflow decreases, and the air membrane 110 returns to its default position, directing the exhaled airflow to the open outlet 100b, which prevents the stoma-exhaled airflow from reaching 100_AC_c and the speech cavity 100VC and the movable speech member 120, and stops speech generation. In some embodiments, the air membrane 110 is heavier than the speech diaphragm 120, so it also vibrates when the exhaled airflow is strong enough to move it, and therefore the air membrane 110 influences the onset of speech. In some embodiments, the air membrane 110 is lighter than the speech diaphragm, and the speech diaphragm influences the onset of speech. In some embodiments, the air diaphragm 110 is heavier than the voice diaphragm, and the air diaphragm 110 influences the initiation of speech. In some embodiments, the interaction between the air diaphragm 110 and the movable voice diaphragm 120 influences automatic speech initiation and termination control.

[0178] In some embodiments, the voice cavity 100VC may include a membrane retainer 120VC. In some embodiments, the membrane retainer 120VC secures the voice diaphragm 120 within the speaker cavity and can be repositioned, attached to, or detached from the third opening 100VC_c to remove, reposition, or replace the diaphragm. In some embodiments, the membrane retainer is disposable after use. In some embodiments, the diaphragm and the membrane retainer are two separate parts, wherein the diaphragm can be detached and discarded when needed. In some embodiments, the diaphragm and the membrane retainer are a single disposable unit.

[0179] In some embodiments, such as Figure 16A As shown, the speaker enclosure 100VC includes a housing 1000VC having a first opening (air inlet) 100VC_a communicating with a flow tube; a second opening (open-type voice outlet) 100c communicating with an inlet via a mouthpiece adapter 100d; and a third opening 100VC_c providing convenient access to the diaphragm retainer 120VC. Figure 16B In some of the illustrated embodiments, air enters the voice cavity housing 1000VC through an internal air inlet 1001VC communicating with a first opening 100VC_a, and exits through an internal voice outlet / exit orifice 1002VC communicating with a second opening 100c of the voice cavity. In some embodiments, a membrane retainer is placed within the voice cavity 100VC such that the membrane is positioned perpendicular to the direction in which airflow passes through the voice cavity from the internal air inlet 1001VC and the internal voice outlet / exit 1002VC.

[0180] In some embodiments, such as Figure 16C As shown, the speech diaphragm 120 is composed of a thin, disc-shaped diaphragm 1200, silicone, or natural or synthetic rubber, with a rectangular or curved segment 1201 in the middle, whereby the disc or middle portion can be flexible to vibrate in response to breathing and generate high-quality speech. In some embodiments, such as Figure 17A As shown, the voice diaphragm 120 is placed in a stationary position (the disc 1200 is fixed within or around the diaphragm holder 120VC, and the central portion 1201 can vibrate freely) for easy replacement. In some embodiments, the disc 1200 is part of the diaphragm; in some embodiments, the disc is made of a rigid material such as plastic, which holds the central portion of the diaphragm in place for easier assembly and replacement in the diaphragm holder.

[0181] In some embodiments, such as Figure 17A As shown, the membrane is placed inside the membrane holder in a static position, where aerodynamic resistance is minimized, and even a minimal breathing force is sufficient to cause the membrane to vibrate. In some embodiments, such as Figure 17BAs shown, the membrane holder places the membrane within the speech cavity 1000VC and near the internal speech outlet / vent port 1002VC, which communicates with the second opening 100c of the speech cavity. In some exemplary embodiments, such as Figure 17B As shown, the membrane retainer places the membrane within the speech cavity, perpendicular to the direction in which air exits within the speech cavity housing 1000VC through the internal speech outlet / exit orifice 1002VC. In some embodiments, exhaled air through the speech cavity exits from the narrow distance between the membrane 120 and the internal speech outlet / exit orifice 1002VC, which readily causes the speech membrane 120 to vibrate. In some embodiments, the membrane retainer 120VC can alter the position of the membrane to be closer to or further away from the internal speech outlet / exit orifice 1002VC, causing the membrane to vibrate in response to lower or higher airflows, thus adapting the device and making it comfortable for individuals with smaller or larger lung capacities.

[0182] In some embodiments, the speaker enclosure 100VC and the diaphragm retainer 120VC are designed to acoustically amplify or attenuate specific portions of the spectrum of the generated sound to improve speech intelligibility. In some embodiments, the speaker enclosure or diaphragm retainer includes an acoustic resonant cavity surrounding the diaphragm, in which the generated sound is acoustically amplified. For example, the speaker enclosure housing 1000VC may have an adjustable depth so that the user can customize the amount of acoustic amplification.

[0183] In some embodiments, the diaphragm retainer can adjust the position of the voice diaphragm within the speaker cavity relative to the voice outlet / exit orifice 1002VC. In some embodiments, a user can adjust the position of the diaphragm retainer relative to the voice outlet / exit orifice 1002VC. In some embodiments, a user can adjust the position of the diaphragm retainer relative to the second opening such that speech initiation occurs with minimal breathing effort closer to tidal breathing, thereby avoiding long-term fatigue. In some embodiments, the diaphragm retainer may have threads (e.g., Figure 17A The 1202VC (in the speaker housing 1000VC) allows the user to adjust the position of the diaphragm to match the patient's expiratory output. In some embodiments, the position of the diaphragm retainer can be automatically adjusted (using a voice coil actuator or stepper motor driven by a pressure sensor placed within the speaker housing) to match the patient's expiratory output. In some embodiments, the position of the diaphragm retainer can be adjusted using a Bluetooth® remote control system, a voice coil actuator, or a miniature stepper motor. Furthermore, as the diaphragm softens due to prolonged use or exposure to respiratory heat and moisture, the position of the voice diaphragm may need to be changed over time.

[0184] In some embodiments, the speaker enclosure can act as a path of least resistance for air, enabling speech generation of the device 100 to be driven by minimal respiratory effort, which can be measured by a respiratory rate measurement method. In some embodiments, minimal respiratory effort will require the device to generate speech at an airflow level close to the patient's maximum tidal breathing. In some embodiments, minimal respiratory effort makes it easier for the patient to generate speech and minimizes fatigue from prolonged use of the device.

[0185] In some embodiments, the voice membrane 120 may be configured to minimize the respiratory effort required to initiate speech, wherein the respiratory effort (tidal breathing pressure measured in kPa and peak airflow measured in liters per minute) can be measured by a respiratory volume assay. In some embodiments, the air membrane may be configured to minimize the respiratory effort required to initiate speech, wherein the respiratory effort (peak airflow measured in liters per minute) can be measured by a respiratory volume assay. In some embodiments, the respiratory effort required to initiate speech is set to any value slightly higher than 1.01 to 2 times the maximum tidal breathing effort or the subject's average tidal breathing effort to minimize patient fatigue during continuous use. In some embodiments, the respiratory effort required to initiate speech may be slightly higher than the subject's average tidal breathing effort to minimize patient fatigue during continuous use.

[0186] In some embodiments, the diaphragm retainer may be configured to minimize the respiratory effort required to initiate speech by maintaining a path of minimum air resistance, thereby enabling the vibration of the speech diaphragm 120 to be driven by minimal respiratory effort, wherein the respiratory effort can be measured by a respiratory volume measurement method. Figure 16B As shown, in some embodiments, the membrane retainer 120VC receives airflow from the inlet 1001VC of the speech cavity and delivers the air to the speech outlet / outlet 1002VC. For example... Figure 17B As shown, in some embodiments, the membrane retainer 120VC includes a mesh structure 1203VC applied to air passing through the membrane retainer, thereby converting a potential jet flow into a laminar flow of air suitable for generating a stabilizing force to vibrate the membrane 120 at lower flow values. The increased surface area of ​​the mesh structure 1203VC increases the total surface area of ​​the air passage through the device and minimizes air resistance within the device. In some embodiments, such as Figure 17BAs shown, the membrane retainer can, for example, have a cylindrical shape, open at one end and closed at the other, with the mesh structure 1203VC implemented on the cylindrical wall. In some embodiments, the surface area of ​​the mesh structure can be increased or decreased, for example, manually by the user, wherein the membrane retainer has two sliding cylinders with mesh structures that slide in close contact with each other. This allows the device to have an adjustable mesh size and therefore adjustable airflow resistance, making the device comfortable for people with a wide range of lung capacities. In some embodiments, the surface area of ​​the mesh structure 1203VC can be quantified from small to large, thereby providing the device with the flexibility to function for people with a wide range of breathing capacities.

[0187] In some embodiments, the voice cavity 100VC and / or voice diaphragm 120VC may be specifically designed to prevent, reduce, or eliminate jamming of the voice diaphragm 120. Diaphragm jamming refers to a condition where a higher vital capacity or excessive airflow forces the voice diaphragm to close the voice outlet / exit orifice 1002VC, causing the vibration of the voice diaphragm 120 to stop adversely. In some embodiments, the voice diaphragm may be adjusted to have a thicker depth or a heavier weight to reduce the jamming effect and make the device more comfortable for individuals with greater respiratory effort, which can be measured by respiratory rate measurement.

[0188] In some embodiments, the voice cavity 100VC and / or diaphragm retainer 120VC may be specifically designed to prevent, reduce, or eliminate obstruction of the voice diaphragm 120. In some embodiments, the voice cavity 100VC may have a fourth outlet that acts as an exhaust device to allow excess air to escape from the cavity and reduce the obstruction effect. This exhaust device is a one-way valve with a higher acoustic resistance compared to the voice outlet / exit orifice 1002VC. When the voice diaphragm is stationary or vibrating, air naturally exits the voice outlet / exit orifice 1002VC; however, when the voice outlet / exit orifice 1002VC is obstructed and closed, the pressure accumulated within the voice cavity housing 1000VC activates the exhaust path, and air escapes from the opening, thereby enabling the voice diaphragm 120 to recover from obstruction to its vibrating position. This can be monitored using a differential pressure sensor, where the breathing pressure within the voice cavity jumps to a local maximum before or when the voice diaphragm is obstructed. In some embodiments, the obstruction exhaust device may be implemented in other parts of the device, including a flow tube or the surface of the voice cavity. In some embodiments, the user can manually activate the blocking exhaust device, for example using a touch sensor placed on the surface of the speaker cavity 100VC or the airflow cavity 100AC.

[0189] In some embodiments, the voice cavity and diaphragm retainer disclosed herein may include a blockage detection pressure or flow sensor. In some embodiments, during or prior to a blockage event, the pressure within the voice cavity jumps and airflow stops. In these embodiments, a blockage detector is operatively connected to the voice cavity. In some embodiments, the voice cavity has a pressure-activated or electronically activated venting mechanism to expel additional air to prevent diaphragm blockage. In some embodiments, the placement of the voice diaphragm relative to a second opening may be adjusted based on input from the blockage sensor to increase or decrease the distance between the diaphragm and the second opening, thereby preventing diaphragm blockage.

[0190] In some embodiments, the membrane retainer adjusts the position of the membrane within the speech cavity, thereby effectively influencing and reducing obstruction. In some embodiments, the membrane retainer uses threads (e.g., Figure 17A This adjustment is performed by the 1202VC in the membrane retainer. In some embodiments, the threaded structure may be designed to include a leaking thread, wherein the thread is designed to be coarse or have intentional clearance to cause air to leak from the cavity. In some embodiments, the leaking thread 1202VC acts as a venting mechanism to release excess pressure accumulated in the cavity and prevent blockage. In some embodiments, the membrane retainer thread 1202VC may be implemented in quantified steps to control the amount of leakage, for example, by making the thread span from coarse to fine to minimize air leakage, wherein minimal air leakage will be better suited for patients with smaller lungs or weaker breathing capacity, to effectively enable the device to be adjustable to accommodate people with different ranges of breathing capacity with minimal obstruction, wherein the user's breathing capacity is measured using spirometry.

[0191] In some embodiments, the speaker cavity disclosed herein may include a humidity detector or sensor. In some embodiments, the humidity detector may alert a subject that saliva / fluid may leak into the speaker cavity, wherein when moisture is detected, the humidity detector alerts the subject, for example via a visual or auditory indicator, of the accumulated humidity inside the device. In some embodiments, the voice cavity 100VC includes an additional water trap to remove saliva or condensation from the device.

[0192] Dental adapter The speaker enclosure 100VC may also include a mouth adapter 100d. In some embodiments, such as Figure 14 As shown, the oral cavity adapter may have an inlet 100d1 that communicates with a second opening (open speech outlet) 100c of the speaker cavity. In some embodiments, the oral cavity adapter 100d is an elongated extension of the open speech outlet 100c. In some embodiments, the oral cavity adapter 100d is an accessory separate from the open speech outlet 100c.

[0193] In some embodiments, the oral adapter has an outlet 100d2, which communicates with the user's oral cavity and is capable of transmitting airflow and sound from the speaker cavity to the subject's oral cavity. In some embodiments, the oral adapter acoustically amplifies speech. In some embodiments, the oral adapter is an oral tube.

[0194] In some embodiments, the oral tube 100d includes a flexible tube for comfortable placement inside the mouth. In some embodiments, the oral tube includes a rigid tube. In some embodiments, the oral tube outlet has a mesh structure that disperses airflow in different directions to prevent the oral tube outlet 100d2 from being blocked by tongue movement. In some embodiments, the oral tube outlet 100d2 is made of a deformable material, such as a flexible silicone ring, to change shape if tongue or vocal tract movement may cause narrowing or blockage of the oral tube outlet 100d2, allowing air to escape from the outlet. In some embodiments, the length or diameter of the oral tube 100d is adjustable to match the breathing capacity of different individuals. In some embodiments, the oral adapter 100d is a disposable unit.

[0195] In some embodiments, the oral tube has an oral end or a saliva trap to limit or prevent saliva from seeping into the device. In some embodiments, the oral tube outlet has a mesh structure to limit saliva from seeping into the tube. In some embodiments, the oral tube 100d has a hydrophobic coating similar to that of the flow tube 133 to prevent saliva droplets or condensation from clogging the tube. In some embodiments, the oral tube 100d has an orifice that can be opened manually or electronically to drain saliva or moisture.

[0196] In some embodiments, the inner diameter of the oral tube can be 0.5-8 mm or larger. In some embodiments, the user can adjust the diameter of the oral tube to increase / decrease breathing resistance. In some embodiments, the length and diameter of the oral tube can be adjusted to increase or decrease the breathing resistance of the device, making it suitable for people with different breathing abilities.

[0197] In some embodiments, the oral tube may have a microphone for picking up generated sounds closer to the mouth and transmitting them to a Bluetooth® or wired speaker implemented on the device or separately to amplify or enhance the resulting sounds in noisy environments.

[0198] Voice quality In some embodiments, the movable speech component 120 may be designed to generate extremely high-quality sound within the natural human voice fundamental frequency range. In some embodiments, the movable speech component or speech cavity may be configured to adjust parameters of the generated speech to tailor the speech for a subject, for example, by relating the fundamental frequency of the voice to a male, female, or non-binary gender fundamental frequency range.

[0199] In some embodiments, the speech diaphragm 120 may be configured to generate a singing sound associated with the fundamental frequency range of a singing pattern. In some embodiments, the speech diaphragm may be configured to generate speech associated with a singing pattern, including but not limited to baritone, mezzo-soprano, soprano, contralto, bass, tenor, contralto, or similar patterns.

[0200] In some embodiments, the speech membrane can be configured to generate sounds associated with tonal or non-tonal languages. In some embodiments, the speech membrane can be configured to generate, for example, sounds associated with Chinese tonal languages. In some embodiments, the speech membrane can be configured to generate breath-driven intonation variations within phonemes suitable for generating Chinese tonal languages. In some embodiments, the speech membrane can be configured to generate sounds of a selected speech quality. In some embodiments, the speech membrane can be configured to generate singing sounds of a selected speech quality.

[0201] In some embodiments, the diaphragm retainer 120VC may be designed to modify the shape of the voice diaphragm 120, for example, by stretching the diaphragm or lifting or pressing the diaphragm in a specific area to increase or decrease the length of the vibrating diaphragm, thereby modifying the parameters of speech generation. In some exemplary embodiments, the diaphragm retainer may be configured to adjust the length or width of the voice diaphragm 120 so that a user can adjust the parameters that generate the speech (e.g., the fundamental frequency). Figure 18A As shown, in some exemplary embodiments, the diaphragm retainer 120VC may be configured to have edges 1204VC that elevate the diaphragm and reduce the length (or width) of the vibrating segment of the speech diaphragm, thereby increasing the fundamental frequency of the generated speech and making the speech sound more feminine. In some embodiments, the diaphragm retainer may be configured to increase this length (or width) of the speech diaphragm, thereby lowering the fundamental frequency of the generated speech and making the speech sound more masculine. In some embodiments, the diaphragm retainer may be provided in pre-designed shapes, quantified with different shapes and lengths of the diaphragm, so that the device can be customized for individuals requiring different speech parameters. For example, Figure 18B An example of a membrane retainer is shown, in which the membrane retainer does not change the fundamental frequency of the speech diaphragm vibration. Figure 18A An example of a membrane retainer for a female voice is shown. In some embodiments, the membrane retainer may be configured to mechanically or electronically actuated via a touch sensor to modify the shape of the membrane (e.g., stretching the membrane or lifting or pressing the membrane at certain points to increase or decrease its length) to generate a high-quality male or female voice. In some embodiments, the membrane retainer may be configured to modify the fundamental frequency of the voice through other mechanical design features.

[0202] In some embodiments, the shape and material composition of the speech diaphragm are specifically designed to generate extremely high-quality speech.

[0203] In some embodiments of the invention, the speech generation diaphragm generates a flat or near-flat spectrum (harmonic peak amplitude variation from ±2dB to ±3dB to ±4dB to ±5dB to ±6dB, spanning a frequency range of any value between 70Hz and 200Hz, 70Hz and 300Hz, 70Hz and 400Hz, 70Hz and 500Hz, 70Hz and 600Hz, 70Hz and 700Hz, 70Hz and 800Hz, 70Hz and 900Hz, 70Hz and 1000Hz, or 70Hz and 300Hz to 2500Hz). Figure 19 (As shown) The spectrum of the source can be measured in the anechoic cavity using a flat-spectrum microphone (e.g., Bruel & Kjaer 4192 model) with a pressure field response of 5 Hz to 7 kHz ± 1 dB (3 Hz to 20 kHz) ± 3 dB, and the source spectrum can be measured reliably. In these measurements, the speech cavity can be driven by airflow from the stoma or simulated airflow from the cervical stoma (e.g., generated by a real-time silent ultrasonic air pump that replicates pre-recorded respiratory pressure or stoma airflow), with the microphone placed within the anechoic cavity at a distance of 30–50 cm from the source.

[0204] In some embodiments, the shape and material composition of the speech diaphragm are specifically designed to generate extremely high-quality speech with broad peaks and narrow valleys in the harmonic spectrum of any value between 70 Hz and 200 Hz, 70 Hz and 300 Hz, 70 Hz and 400 Hz, 70 Hz and 500 Hz, 70 Hz and 600 Hz, 70 Hz and 700 Hz, 70 Hz and 800 Hz, 70 Hz and 900 Hz, 70 Hz and 1000 Hz, or 70 Hz and 300 Hz to 2500 Hz (e.g., as shown in the original text). Figure 19 (As shown).

[0205] In some embodiments, a broad peak in the harmonic spectrum of extremely high-quality speech can be defined, wherein most of the energy of the peak (calculated in the spectrum or power spectral density as an integral of the spectral amplitude or power spectral density values ​​around the peak over the peak bandwidth) is distributed over more than 20%, more than 30%, or more than 40% of the peak bandwidth, where the peak bandwidth is the difference between the frequency values ​​associated with the two troughs before and after the peak (e.g., as shown in the figure). Figure 19 (As shown).

[0206] In some embodiments, the flat or semi-flat harmonic structure of the generated speech and the inclusion of broad peaks in the spectrum significantly improve the excitation of the vocal tract formant, thereby providing clear vowels and consonants in the phonation. In some embodiments, the flat or semi-flat harmonic structure and broad spectrum of the generated speech produce extremely high-quality speech that is close to or similar to natural sound. In some embodiments, the spectral peaks of the speech diaphragm (e.g., as shown in the figure) Figure 19 (As shown) is converted into a waveform that approximates the natural glottal speech waveform in the time domain.

[0207] In some embodiments, the material composition of the voice diaphragm is specifically designed to generate extremely high-quality speech. For example, the voice diaphragm 120 is made of a thin silicone membrane with a flexibility (measured in Shore A hardness) varying between 20 and 50, and the shape (width) of the voice diaphragm varies from 6 to 15 mm. In some embodiments, the membrane thickness varies from 0.1 to 0.6 mm.

[0208] In some embodiments, the shape of the voice diaphragm is specifically designed to generate extremely high-quality speech. In some embodiments, the voice diaphragm is made of a flexible sheet, such as natural or synthetic rubber or silicone, having an inherent resonant frequency within the fundamental frequency range of the human voice (which can vary from 70 Hz to over 300 Hz). In some embodiments, the voice diaphragm is made of a flexible sheet, such as natural or synthetic rubber or silicone, having flexibility (e.g., a thickness of any value in the range of 0.05 to 0.6 mm). In some embodiments, such as Figure 16C As shown, the speech diaphragm 120 can be cut into different shapes, including, for example, a circular disc frame 1200, which is connected to a rectangular, circular, elliptical, or irregular shape 1201 to generate the irregularity of natural speech vibrations. Figure 17A As shown, in some embodiments, the voice diaphragm is a thin, adjustable circular disc frame that can be attached to or detached from the placeholder slice 1201VC of the diaphragm holder 120VC. In some embodiments, the width of the vibrating element of the diaphragm 1201 can be, for example, about 4 to 16 mm. In some embodiments, the length of the vibrating element of the diaphragm 1201 can be, for example, 6 to 20 mm. In some embodiments, the Shore A stiffness of the vibrating element of the diaphragm 1201 can be, for example, 10 to 50, to easily vibrate in response to the airflow exhaled by a person. Figure 16C As shown, in some embodiments, the voice diaphragm includes a circular disk 1200, wherein the vibrating element 1201 of the diaphragm may, for example, have a rectangular shape 1201 of, for example, 5 to 16 mm × 6 to 20 mm and a Shore A hardness of 20-50, to generate extremely high-quality human speech. In some embodiments, the vibrating element 1201 of the diaphragm may have other shapes.

[0209] In some embodiments, the speech diaphragm can be configured to generate a sound with a desired fundamental frequency (pitch). In some embodiments, the speech diaphragm can be configured to generate a sound with a pitch at a specific frequency. In some embodiments, changing... Figure 19 The fundamental frequency of the spectrum of the exemplary speech diaphragm provides a sound source for speech with extremely high-quality natural sound, and the possibility of generating male, female, or non-binary gender speech. In some embodiments, the material, flexibility (measured in Shore A hardness), thickness, or shape of the speech diaphragm 120 can be adjusted to allow the fundamental frequency of the source's harmonic spectrum to span from male (70-150 Hz) to non-binary gender (130-160 Hz) to female (160-240 Hz), and even higher values ​​for children. In some embodiments, the speech diaphragm can be configured to generate a sound with a pitch of any value from about 60 Hz to less than 350 Hz. In some embodiments, the speech diaphragm can be configured to generate a sound with a pitch of at least or about 60 Hz to at least or about 350 Hz. In some embodiments, the speech diaphragm can be configured to generate a sound with pitch in quantization steps, wherein the pitch is generated on a quantized frequency scale.

[0210] In some embodiments, the vibrating portion of the speech diaphragm 1201 can be cut into different shapes to modify the pitch or spectrum of the speech. For example, Figure 16C The length of the mid-vibration segment 1201 can be reduced from 20 mm to 6 mm, thereby increasing the fundamental frequency from approximately 70 Hz, the pitch of male voices, towards a pitch exceeding 160 Hz, in female voices. Other parameters that can be changed include, for example, amplification or reduction. Figure 19 The width of the spectral peaks in the harmonic spectrum of the generated speech. For example, Figure 16C The width of the mid-vibration segment 1201 can be increased from 5 mm to 12 mm or more, thereby providing a wider peak in the spectrum of the generated speech. This can translate into improved excitation of the vocal tract and improved formant shaping, resulting in improved speech intelligibility and clarity. In some embodiments, the edges of the speech diaphragm can be cut with curved edges and specific irregular shapes, such as... Figure 16C As shown in the example, the generated sound is designed to mimic the natural, irregular vibrations of the human vocal cords. In some embodiments, the radius of the outer disc 1200 may be, for example, 10 to 40 mm, and the width may be 0.1 to 10 mm, to enhance the harmonic structure of the speech spectrum. In some embodiments, the radius of the outer disc 1200 may be, for example, 10 to 40 mm, and the width may be 0.1 to 10 mm, to accommodate different users' breathing forces. In some embodiments, the edges of the outer disc 1200 may be cut with non-straight edges, for example, as shown in the example. Figure 16C The example shows curved edges or irregular shapes to produce a sound that mimics the irregular and natural vibrations of the human vocal cords.

[0211] In some embodiments, the vibrating segment of the speech diaphragm 1201 or the edge of the outer disk 1200 may be reinforced with a thicker or thinner material at the center or edge to filter out or enhance specific portions of its vibrational mode harmonic spectrum and the resulting speech. For example, providing a thinner recircle at the center of the diaphragm 1201 will amplify higher frequencies in the sound spectrum because the diaphragm will vibrate at a faster rate in response to similar airflow excitation, thus providing better intelligibility in high formant vowels (e.g., [i]). In another example, providing irregular edges to the diaphragm can allow the diaphragm to begin vibrating under lower airflow, thereby reducing the speech initiation and breathing effort of the device when needed.

[0212] In some embodiments, the speech diaphragm 120 may be made of flexible silicone or natural or synthetic rubber, wherein the diaphragm size and flexibility are specifically selected, for example, the flexibility (measured in Shore A hardness) may vary at any value between Shore A 10 and 50, thereby enabling the diaphragm to respond to changes in respiration in less than 5 milliseconds to the onset and end of speech. This minimal delay translates into a source that rapidly switches between voiced and unvoiced phonations, enabling the patient to generate intelligible phonations with clear voiced and unvoiced phonemes. In some embodiments, the speech diaphragm may be specifically designed to generate rapid vibrational patterns associated with laughter. In some embodiments, the speech diaphragm may be specifically designed to convey breath-driven pitch variations in speech to generate emotionally expressive or singing speech.

[0213] In some embodiments, the membrane retainer may be configured to modify the fundamental frequency during phonation or singing. In some embodiments, the membrane retainer may be designed to modify the membrane shape mechanically or electronically (e.g., driven by a touch sensor) to stretch / relax the membrane as the patient phonates or sings, or to lift or press the membrane relative to the membrane retainer at certain points (e.g., to increase or decrease the length of the membrane), thereby generating a wider range of note and pitch variations for phonation or singing.

[0214] Speech generation apparatus and method The following embodiments are provided as further preferred examples of the speech generation system 100. These are examples and are not intended to identify key or essential features of the claimed subject matter, nor are they intended to limit the scope of the claimed subject matter.

[0215] Refer to Figure 2. Figure 13 Or, as in the exemplary embodiment of Figure 20, the speech generation system 100 disclosed in this invention includes an artificial larynx that can be used as a patient with aphonia.

[0216] In some preferred embodiments, the artificial larynx can be used in a hands-free manner. In some embodiments, the artificial larynx can be used hands-free, wherein the artificial larynx does not require manual handling by the user. (Reference) Figure 13In some embodiments, the flow tube 133 may be made of a rigid material to hold the speech generation system in place without requiring the user to hold the device. In some embodiments, the weight of the device and the flexibility of the flow tube can be adjusted to hold the device in place within the mouth without using either hand, thereby enabling automatic two-way breathing / voice control and hands-free functionality.

[0217] In some other preferred embodiments, the artificial larynx can be used in a hands-free manner, wherein the artificial larynx is worn around the ear as a headset. Referring to an exemplary embodiment of FIG20, the speech generation system 100 can be used as an artificial larynx worn around the ear as a headset, wherein the user can generate speech without manually holding the device. Referring to an exemplary embodiment of FIG20, the airflow cavity is connected to and attached to the stoma accessory via a medical-grade airway barrier, and the speaker cavity is placed along the ear of the human subject. The oral tube 100 is detachable, or can be placed outside the mouth of the human subject when not in use. In some embodiments, including Figure 13 or Figure 20B In one embodiment, the artificial larynx can be used without manual intervention, while in other arrangements, such as where the artificial larynx is worn as a neck strap behind the user's neck.

[0218] In some embodiments, the speech generation system 100 may be partially usable and then discarded. In some embodiments, the speech generation system 100 may be designed to be fully usable and then discarded. In certain embodiments, all or part of the speech generation system 100 is intended for one-time or short-term use, wherein components of the speech generation system 100 as described herein are intended to be discarded after a period of use. In some cases, these different components of the speech generation system 100 may be discarded after different periods of use, ranging from half an hour to three years.

[0219] In some embodiments, the stoma accessory or medical-grade respiratory barrier of the speech generation system 100 may be discarded daily. In some embodiments, the air cavity includes a medical-grade respiratory barrier and may be discarded daily along with the medical-grade respiratory barrier. In some embodiments, the air cavity is separate from the medical-grade respiratory barrier, can be used multiple times, and is discarded after a longer period of time, wherein the medical-grade respiratory barrier may be discarded daily. In some embodiments, the airflow cavity membrane, sound chamber membrane, sound chamber cavity, flow tube, and oral tube of the artificial larynx may be discarded after one or more days.

[0220] In some embodiments, a method for generating speech is disclosed, the method involving a speech generation system 100 in contact with a cervical stoma, wherein the contact involves positioning and sealing a device over the user's stoma. Similarly, in some cases, the contact involves connecting the device to a medical-grade airway barrier connected to a stoma accessory and inserting an oral tube into the subject's mouth. In some other cases, when the airflow cavity contains a medical-grade airway barrier, the contact involves inserting the device into a stoma accessory unit.

[0221] The speech generation system 100 may consist of components provided in a disposable form, including an airflow chamber and / or a medical-grade airway barrier. The speech generation system 100 may be designed to connect to and use pre-existing (commercially available) stoma attachments (e.g., baseplates or laryngostomy buttons) or commercially available medical-grade airways barrier (e.g., HMEs). The speech generation system 100 may be designed to connect to a specially designed stoma attachment or medical-grade airway barrier as part of a device.

[0222] In some embodiments, a method for generating extremely high-quality speech is described, involving a subject exhaling through their stoma, delivering expiratory air into an airflow chamber, and then automatically directing the airflow into a speech chamber using a movable air device to generate speech based on the exhalation. Furthermore, the movable air device is designed to be disposable and replaceable after use.

[0223] In some embodiments, a method for generating speech in a subject is disclosed, wherein the method involves generating speech within a speech cavity using a movable speech component and automatically guiding the generated speech and airflow into the subject's mouth. Furthermore, the movable speech component is designed to be disposable and replaceable after use. Additionally, the movable speech component can be customized to create speech with a selected speech spectrum or specific pitch or frequency.

[0224] In some embodiments, the present invention provides a method for generating speech, wherein a subject exhales through his stoma, delivering the exhaled air through an airflow cavity, redirecting it using a movable air element, through a flow tube, through a movable speech component, through an oral tube 100d into the subject's mouth, and generating speech in the mouth based on the exhaled air.

[0225] In some examples, the present invention provides a method for generating speech, wherein a subject exhales through his stoma, directs the exhalation through a pressure-activated switch, through a flow tube, through a speech membrane, through an oral tube into the subject's mouth, and generates speech in the mouth based on the exhalation.

[0226] In some embodiments, the present invention describes a method for generating speech, wherein a subject exhales through his stoma, delivers the exhaled air through a pressure-activated switch, through a movable speech component into the subject's mouth, and generates speech in the mouth based on the exhaled air.

[0227] In some examples, a method for generating speech is disclosed, which involves a subject exhaling through his stoma, guiding the exhalation through a pressure-activated switch, through a speech membrane into the subject's mouth, and generating speech in the mouth based on the exhalation.

[0228] In some examples, a method for generating speech is disclosed, which has a wide range of customizable parameters, such as adjustable airflow resistance or adjustable speech parameters, to provide easy and comfortable use for people with different breathing abilities, including, for example, people with small, medium or large lung capacity.

[0229] The alternative embodiments may also be considered to broadly include the parts, elements, steps and / or features mentioned or specified herein, whether these parts, elements, steps and / or features are alone or in any combination of two or more, and any particular complete object mentioned herein has a known equivalent in the art to which this invention relates, such known equivalents shall be considered to be incorporated herein as if listed separately.

[0230] Although preferred embodiments have been described in detail, it should be understood that many modifications, alterations, substitutions or alterations can be made to the present invention by those skilled in the art without departing from the scope of the invention.

[0231] Unless the context explicitly requires otherwise, the words “comprising” and “including” in the specification and claims should be interpreted as inclusive rather than exclusive or exhaustive; that is, they should be interpreted as “including but not limited to”.

[0232] In this specification and the appended claims, unless the context otherwise requires, the terms “and” and “or” as used in the appended documents are intended to include one, a subset or more, or all of the options connected by “and” and “or” in a sentence. The terms “and” and “or” as used may or may not include the options connected by “and” and “or”.

Claims

1. A breathing-driven speech generation system, comprising: a) An airflow cavity, wherein the airflow cavity includes a first opening, a second opening, and a third opening, and the airflow cavity defines an air passage between the first opening, the second opening, and the third opening. The first opening of the airflow cavity is configured to communicate with, be sealed to, or contain a medical-grade respiratory barrier, wherein the medical-grade respiratory barrier is connected to the user's cervical stoma. The second opening of the airflow cavity is configured to communicate with open air. The airflow chamber includes a first movable member configured to function as a multi-directional air valve to guide air within the airflow chamber between the first opening, the second opening, or the third opening; and b) A voice cavity, the voice cavity including an air inlet and a voice outlet, wherein the air inlet of the voice cavity is connected to a third opening of the airflow cavity, and the voice outlet of the voice cavity is connected to the user's oral cavity. The voice cavity includes a second movable member that generates sound based on the air exiting the airflow cavity, and the generated sound exits the voice cavity through the voice outlet.

2. The speech generation system according to claim 1, wherein, The first opening of the airflow cavity is configured to include a medical-grade respiratory barrier, be connected to the medical-grade respiratory barrier, or be sealed onto the medical-grade respiratory barrier, wherein the medical-grade respiratory barrier communicates with the stoma using a stoma accessory, the stoma accessory comprising: A substrate capable of covering, attaching to, or detaching from the skin around a user's cervical stoma; and a substrate capable of at least partially penetrating into the user's cervical stoma.

3. The speech generation system according to any one of the preceding claims, wherein, The air inlet of the speaker enclosure is connected to the air outlet of the airflow chamber through an air duct or flow tube.

4. The speech generation system according to any one of the preceding claims, wherein, The voice output of the speaker cavity is connected to the user's mouth via an oral adapter or oral tube.

5. The speech generation system according to any one of the preceding claims, wherein, The first movable component enables the speech generation system to automatically switch between at least two modes of bidirectional breathing or speech generation without removing the device from its connection with the cervical stoma.

6. The speech generation system according to any one of the preceding claims, wherein, The second movable component can be configured to generate extremely high-quality speech.

7. The speech generation system according to any one of the preceding claims, wherein, The second movable component can be configured to generate a selected or preset fundamental frequency (pitch) sound, including male, female, or non-binary gender speech quality.

8. The speech generation system according to any one of the preceding claims, wherein, The interaction between the first movable member and the second movable member enables the system to automatically inhale / exhale, automatically control the start and end of speech, and automatically generate speech without removing the device from the communication with the cervical stoma.

9. The speech generation system according to any one of the preceding claims, which uses a medical-grade respiratory barrier to provide sanitary connectivity between the device and the cervical stoma.

10. The speech generation system according to any one of the preceding claims, wherein, Medical-grade respiratory barriers include heat and moisture exchangers (HMEs) that can be attached, detached, or included in the system.

11. The speech generation system according to any one of the preceding claims, wherein, The stoma accessories include or are similar to the baseplate, laryngostomy button or tracheostomy tube used by patients who have undergone laryngectomy or tracheostomy.

12. The speech generation system according to any one of the preceding claims, wherein, The airflow chamber also includes a bypass mode that can be manually activated by the user to allow for coughing and hyperventilation without removing the device from its connection to the cervical stoma.

13. The speech generation system according to any one of the preceding claims, wherein, The airflow chamber also includes a bypass mode that uses a movable window, wherein when the window is closed, air exits the airflow chamber through an outlet, and the user can manually open the window when it is necessary to disable the outlet without removing the device from the connection with the cervical stoma.

14. The speech generation system according to any one of the preceding claims, wherein, The first movable component is a membrane, which comprises silicone, natural or synthetic rubber, medical-grade silicone or other plastic or thin metal materials.

15. The speech generation system according to any one of the preceding claims, wherein, The second movable component is a membrane, which contains silicone, natural or synthetic rubber, medical-grade silicone or other flexible materials.

16. The speech generation system according to any one of the preceding claims, wherein, The first membrane can be configured to a predetermined size, which varies in mass, thickness and flexibility, so that the operation of the device at the start or end of voice is close to the tidal breathing capacity of different users.

17. The speech generation system according to any one of the preceding claims, wherein, The second membrane can be configured to generate a sound with an adjustable or preset fundamental frequency (pitch) between 80 Hz and 350 Hz.

18. The speech generation system according to any one of the preceding claims, wherein, The second membrane can be configured to generate extremely high-quality speech with a near-flat or semi-flat harmonic spectrum, wherein the peak amplitude of the spectral harmonics varies from ±2dB to ±3dB to ±4dB to ±5dB to ±6dB, spanning a frequency range of any value between 60Hz to 200Hz, 60Hz to 300Hz, 60Hz to 400Hz, 60Hz to 500Hz, 60Hz to 600Hz, 60Hz to 700Hz, or 60Hz to 800Hz, or 60Hz to 300Hz to 1500Hz.

19. The speech generation system according to any one of the preceding claims, wherein, The second membrane can be configured to generate a variable fundamental frequency (pitch) for breathing drive used in singing.

20. The speech generation system according to any one of the preceding claims, wherein, The system can be configured to be used completely without manual intervention.

21. The speech generation system according to any one of the preceding claims, wherein, The speech generation system is configured to be placed on, around, or behind the neck of a human subject.

22. The speech generation system according to any one of the preceding claims, wherein, The system is configured to be placed on the ear of a human subject.

23. The speech generation system according to any one of the preceding claims, wherein, The system includes adaptable, adjustable, or preset parameters that enable the system to generate speech with different pitch values ​​in the range of 60 Hz to approximately 350 Hz.

24. The speech generation system according to any one of the preceding claims, wherein, The second membrane can be configured to a predetermined size, which varies in quality, thickness, and flexibility, to generate a range of pitches with a selection of male, female, or non-binary gender speech quality.

25. The speech generation system according to any one of the preceding claims, wherein, The second diaphragm is placed in a diaphragm retainer, wherein the diaphragm retainer is connected within the speech cavity, and wherein the diaphragm retainer is configurable to modulate the pitch or spectrum of the sound generated by the second diaphragm to generate a range of selected or preset pitch values, including male, female, or non-binary gender speech quality.

26. The speech generation system according to any one of the preceding claims, wherein, The second membrane is made of natural rubber or medical-grade silicone, with a thickness of 0.05 to 0.6 mm and a flexibility of Shore A 10-60. By changing the thickness, shape, and flexibility of the membrane, the device can generate a wide range of pitches from 80 Hz to 350 Hz for men, women, non-binary genders, and children.

27. The speech generation system according to any one of the preceding claims, wherein, The second membrane is made of a thin film of silicone, natural rubber or similar flexible material, cut into shapes including straight or curved edges or specific irregular shapes to generate the natural irregular vibrations of the human vocal cords.

28. The speech generation system according to any one of the preceding claims, wherein, The second membrane is placed in a membrane retainer, wherein the membrane retainer is easily placed in or removed from the speech cavity.

29. The speech generation system according to any one of the preceding claims, wherein, The second membrane is fitted in a membrane retainer within the speech cavity, wherein the membrane retainer modifies the respiratory airflow from turbulence to a controlled sum of parallel airflows, which enables the second membrane to resonate uniformly and generate vibrations close to the membrane's natural resonant frequency and within the frequency range of human speech.

30. The speech generation system according to any one of the preceding claims, wherein, The system includes adaptable, adjustable, or preset parameters that enable the system to be adjusted to suit users with different lung capacities, or to generate speech with a breathing effort close to tidal breathing effort for different users.

31. The speech generation system according to any one of the preceding claims, wherein, The second membrane is placed in a membrane retainer, wherein the position of the membrane within the speech cavity is adjusted by the membrane retainer, including by using a threaded mechanism to adjust the breathing effort at the onset of speech to suit the user's lung capacity.

32. The speech generation system according to any one of the preceding claims, wherein, The first or second membrane parameter, including thickness, shape, or flexibility, can be configured to cause the device’s speech generation initiation to correspond to a breathing airflow that is closer to the user’s tidal breathing level, thereby minimizing user fatigue.

33. The speech generation system according to any one of the preceding claims, wherein, The first or second membrane parameter, including thickness, shape, or flexibility, can be quantified to enable the speech generation system to function for subjects with low, medium, or high airflow respiratory output.

34. The speech generation system according to any one of the preceding claims, wherein, The first or second membrane parameters, including material and shape, can be configured to cause the device’s speech generation initiation to correspond to a breathing airflow that is closer to the user’s tidal breathing level, thereby minimizing user fatigue.

35. The speech generation system according to any one of the preceding claims, wherein, The membrane retainer can be configured to minimize the aerodynamic drag of the device during voice generation, thereby minimizing user fatigue.

36. The speech generation system according to any one of the preceding claims, wherein, The first opening of the airflow chamber is connected to the user's cervical stoma via a medical-grade respiratory barrier, which is capable of: a) Implemented within and as part of the airflow cavity, capable of being attached to or detached from the airflow cavity; or b) Separated from and connected to the airflow cavity, capable of being attached to or detached from the airflow cavity.

37. The speech generation system according to any one of the preceding claims, wherein, The airflow cavity is connected to the cervical stoma via a stoma accessory, which is capable of: a) is part of the speech generation system and can be attached to or detached from the medical-grade respiratory barrier; or b) Separable from the device, capable of being attached to or detached from the device through the medical-grade respiratory barrier.

38. The speech generation system according to any one of the preceding claims, wherein, The airflow chamber and medical-grade respiratory barrier can be detached from the flow tube to maintain communication between the speech chamber and the stoma accessory and protect the airway when needed.

39. The speech generation system according to any one of the preceding claims, wherein, The airflow cavity includes a stable housing and a detachable housing. The stable housing can maintain communication with the stoma accessory when needed. The detachable housing is in communication with the flow tube and the speech cavity. The detachable housing can be detached from the stable housing when needed to maintain the portability of the device.

40. The speech generation system according to any one of the preceding claims, wherein, The voice cavity includes an exhaust mechanism that discharges excess air pressure accumulated within the voice cavity, thereby preventing voice interruption and blockage of the second diaphragm.

41. The speech generation system according to any one of the preceding claims, wherein, The exhaust mechanism is activated by mechanical or electronic means.

42. The speech generation system according to any one of the preceding claims, wherein, The membrane retainer enables the repositioning of the second membrane to avoid membrane blockage and speech interruption, wherein the repositioning can be activated mechanically or electronically.

43. The speech generation system according to any one of the preceding claims, wherein, Some or all of the components of the speech generation system are disposable and replaceable once they are available.

44. The speech generation system according to any one of the preceding claims, wherein, The first or second movable voice component is disposable and easily replaceable once it is available.

45. The speech generation system according to any one of the preceding claims, wherein, The air inlet of the speaker cavity is connected to the air outlet of the airflow cavity through a flow tube.

46. ​​The speech generation system according to any one of the preceding claims, wherein, The flow tube is connected to the airflow chamber via a mechanical clamp and can be attached or detached as needed.

47. The speech generation system according to any one of the preceding claims, wherein, The flow tube is connected to the airflow cavity via a magnetic clamp and can be attached or detached as needed.

48. The speech generation system according to any one of the preceding claims, wherein, The flow tube is coated with an anti-condensation coating, including an anti-condensation coating containing a hydrophobic coating.

49. The speech generation system according to any one of the preceding claims, wherein, Some devices or flow channels are made of a selectively semi-permeable material that allows moisture to escape from the system while keeping the airflow inside the device to prevent or reduce condensation.

50. The speech generation system according to any one of the preceding claims, wherein, The airflow cavity or voice cavity includes one or more water trapping mechanisms to remove condensation or saliva from the device, wherein the water trapping mechanism is activated mechanically or electronically.

51. The speech generation system according to any one of the preceding claims, wherein, The flow tube or oral tube includes one or more water trapping mechanisms, such as a piston, a double tube with an insulating wall, a double tube with an electronically insulating wall, or a double tube with an anti-condensation coating.

52. A breathing-driven speech generation system, comprising: A first movable component and a second movable component are in communication with the user's breathing airflow, wherein the first movable component and the second movable component enable the user to automatically start / stop speech, automatically generate speech, and breathe in both directions. a) Wherein, the first movable component is in airflow communication with the user's cervical stoma via a hygienic medical-grade respiratory barrier. b) wherein the first movable component serves as a multi-directional air valve, enabling the user to inhale, exhale, or automatically generate speech. c) wherein the second movable member receives an expiratory airflow redirected by the first membrane to generate speech. d) wherein the second movable member is adjustable to generate extremely high-quality speech, and e) wherein the second movable member is adjustable to generate speech at different pitches, including male / female voices or non-binary gendered speech.

53. The speech generation system according to claim 52, further comprising: An airflow cavity, wherein the airflow cavity houses the first movable member: a) wherein the airflow cavity is attached to, connected to, or sealed on the medical-grade respiratory barrier; b) Wherein, the medical-grade respiratory barrier is connected to or communicates with the stoma accessory; and a) wherein the first movable component serves as a multi-directional air valve, enabling the user to inhale, exhale, or automatically generate speech.

54. The speech generation system according to claim 52, further comprising: An airflow chamber, wherein the airflow chamber provides a bypass mode to disable speech generation, enabling the user to cough and breathe freely when needed without removing the airflow chamber from the cervical stoma.

55. The speech generation system according to claim 53, further comprising: An airflow chamber, wherein the airflow chamber and the medical-grade respiratory barrier included or attached thereto are detachable from the rest of the system and remain in communication with the stoma accessory to protect the airway.

56. The speech generation system according to claim 52 further includes a speech cavity, the speech cavity including a second movable member, the second movable member being capable of generating speech of extremely high quality.

57. The speech generation system of claim 52, further comprising a speech cavity, the speech cavity using the second movable member, wherein, The second movable member is a membrane and has a flat or semi-flat harmonic spectrum over a frequency range of any frequency value from 60 Hz to up to 1500 Hz.

58. The speech generation system according to claim 52, wherein, The first movable component or the second movable component is a flexible membrane.

59. The speech generation system according to claim 52 further includes a speech cavity, wherein, The speech cavity includes a membrane retainer that can be adjusted before or during use to modify the speech cavity membrane configuration, thereby changing speech parameters, including the pitch of phonation or singing.

60. The speech generation system according to claim 52, wherein, The system parameters are adjustable to make the device comfortable for different users' breathing abilities. a) Among them, The first component is adjustable to match the breathing capacity of different users, thereby acting as a multi-directional air valve for users with a wide range of breathing capacities. b) Wherein, the second component is adjustable to match the breathing capacity of different users, thereby generating speech for users with a wide range of breathing capacities; and c) Wherein, the aerodynamic resistance of the membrane retainer is adjustable so that the device operates in accordance with the tidal breathing effort of different users.

61. The speech generation system according to claim 52, wherein, The generated voice can be adjusted according to different users' voice preferences: a) wherein the second component is adjustable to generate speech of a selected gender, including male, female, or non-binary gender; and b) wherein the membrane holder is adjustable to customize the pitch or spectral content of the generated speech.

62. The speech generation system according to claim 52, wherein, The first movable member or the second movable member can be adjusted so that the start and end of the device's voice and the force of voice generation are closer to the user's tidal breathing, thereby minimizing user fatigue.

63. The speech generation system according to claim 52, wherein, The voice cavity or membrane retainer can have customizable parameters, such as adjustable aerodynamic resistance, to provide easy and comfortable use for people with different breathing abilities, including, for example, people with small, medium or large lung capacity.

64. The speech generation system according to claim 52 further includes an airflow cavity and a detachable portable speech cavity, wherein, The connection between the airflow cavity and the speech cavity can be removed when needed to provide portability for the device.

65. The speech generation system of claim 52 further includes some or all of the disposable components to ensure hygienic use.

66. The speech generation system according to claim 52, wherein, The system is designed for manual operation.

67. The speech generation system according to claim 52, wherein, The medical-grade respiratory barrier includes a sputum / sputum blocking feature to prevent sputum / sputum from exiting the stoma and interrupting the normal function of the device.

Images