A bionic oral cavity sound production device, robot

Abstract

The utility model provides a kind of bionic oral cavity sound production device, robot.The utility model's bionic oral cavity sound production device includes sound production element, the sound production element is arranged in sound production box, the sound production box includes movable component, the movable component is used to change the form of the content space of the sound production box;The one end of the sound production box can be opened and closed;The sound production box is configured to imitate human oral cavity shape;The movable component is configured to simulate the movement of human lips, the transmission mechanism is used to drive the movable component movement in multiple directions;The robot provided by the utility model includes the above-mentioned bionic oral cavity sound production device.The utility model changes the form of sound production box by movable component drive, realizes and human sound production physiological process is matched with dynamic adjustment.

Description

Technical Field

[0001] This application relates to the field of robot voice interaction technology, and more specifically, to a bionic oral cavity speech device, a robot, and a dynamic bionic oral cavity speech control method. Background Technology

[0002] With the rapid development of artificial intelligence and robotics, voice interaction has become one of the core methods of human-computer interaction. Currently, mainstream robot voice generation technologies primarily rely on electronically synthesized speech systems, achieving voice functionality through digital signal processing and speaker output. While some technical solutions attempt to physically simulate human vocal organs, such as using fixed-shape cavity structures to mimic the oral or nasal cavities, these solutions have certain limitations.

[0003] A static cavity cannot simulate the dynamic changes in the oral cavity shape during human vocalization. In real human vocalization, the shape and volume of the resonance cavity are dynamically adjusted through movements such as jaw opening and closing and changes in lip shape; this is a key physiological mechanism for producing rich speech features. However, the cavity shape of existing bionic vocalization devices remains fixed, resulting in significant deficiencies in vowel differentiation, consonant clarity, and the natural fluency of transitions between phonemes. It is difficult to achieve subtle and crucial speech features, such as distinguishing between / i / and / u / by whether or not the lips are rounded.

[0004] Furthermore, existing technologies lack an effective mechanism for converting speech parameters into cavity morphology control commands in real time, resulting in a disconnect between hardware structure and control algorithms. This disconnect prevents the system from precisely controlling the morphological changes of the vocal cavities, making it difficult to achieve dynamic adjustments that match the physiological processes of human vocalization.

[0005] Another significant drawback is that current technology cannot achieve the coordinated operation of multiple cavities. Human vocalization is a complex process involving the coordinated action of multiple resonating cavities, such as the oral cavity and nasal cavity. However, current technology often focuses only on simulating a single cavity, making it difficult to reproduce the complete biomimetic vocalization process, especially when dealing with speech features that require the coordination of multiple cavities, such as nasal sounds.

[0006] To address the aforementioned issues, existing technologies urgently need improvement. Utility Model Content

[0007] The purpose of this application is to provide a bionic oral cavity sound-producing device, robot, and dynamic bionic oral cavity sound-producing control method, which has the advantage of achieving anthropomorphic natural sound production by dynamically adjusting the shape of the sound cavity.

[0008] This application provides a biomimetic oral cavity sound-generating device, the technical solution of which is as follows: A biomimetic oral cavity sound-generating device includes a sound-generating element disposed within a sound-generating box. The sound-generating box includes a movable component, which is used to change the shape of the internal space of the sound-generating box. One end of the sound-generating box is openable and closable. The sound-generating box is constructed to mimic the shape of the human oral cavity. The movable component is configured to simulate the movement of the human lips, and a transmission mechanism is used to drive the movable component to move in multiple directions.

[0009] Furthermore, the movable component is configured to simulate the movement of human lips, and the movable component is made of an elastic material.

[0010] Furthermore, the bionic oral sound-generating device also includes a fixed component; the movable component, facing the inside of the sound-generating box, mimics the shape of the inner wall of the human mandible; the movable component is connected to the fixed component.

[0011] Furthermore, the sound-emitting box also includes a second sound-emitting cavity. The sound-emitting box includes a first side and a second side opposite to each other. The first side includes the movable member. The second side is disposed adjacent to the second sound-emitting cavity. The second sound-emitting cavity is provided with an opening. The second sound-emitting cavity is constructed in the shape of a nasal cavity.

[0012] Furthermore, the movable component is installed to the sound-generating box via a movable connector, the movable component is connected to a transmission mechanism, and the transmission mechanism is connected to a power source.

[0013] Furthermore, the sound-generating box is configured to simulate the acoustic characteristics of the human throat and / or oral cavity.

[0014] Furthermore, there are multiple movable components, and the multiple movable components are connected to each other by connectors.

[0015] This application also provides a robot including any of the above-described bionic oral speech device.

[0016] The beneficial effects of this utility model are as follows: The bionic oral voice-generating device and robot provided in this application include a voice-generating element set in a voice-generating box with movable components. The movable components drive the shape change of the voice-generating box to achieve dynamic adjustment that matches the physiological process of human voice generation. Attached Figure Description

[0017] Figure 1 This is a structural schematic diagram of an embodiment of the present utility model.

[0018] Figure 2 This is a schematic diagram of a transmission mechanism according to an embodiment of the present invention.

[0019] Explanation of reference numerals in the attached drawings: 1-Sound-generating box; 2-Moving component; 3-Transmission mechanism; 31-First connecting rod; 32-Second connecting rod; 33-Third connecting rod; 311-First rotating connector; 321-Second rotating connector; 331-Third rotating connector; 332-Fourth rotating connector. Detailed Implementation

[0020] The following will be combined with the provisions of this application. Figure 1 and Figure 2 The technical solutions in this application are clearly and completely described herein. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] In existing technologies, robot voice technology mostly employs fixed-shape resonant cavity structures, which cannot simulate the dynamic physiological processes of human vocal organs. Static cavities result in insufficient vowel differentiation, unclear consonant pronunciation, and difficulty in achieving natural transitions between phonemes. For example, when simulating closed-mouth sounds, traditional devices, lacking shape adjustment capabilities, cannot accurately reproduce the effect of jaw closure on the resonant cavity volume.

[0022] To address the aforementioned issues, this application introduces movable components to alter the internal spatial shape of the sound-generating cavity, effectively simulating oral cavity opening and closing movements, thereby improving acoustic characteristics.

[0023] Therefore, this application proposes a biomimetic oral cavity sound-generating device including a sound-generating element disposed within a sound-generating box 1 having a movable member 2. The movable member 2 is used to change the shape of the internal space of the sound-generating box 1, and one end of the sound-generating box can be opened and closed. Specifically, the internal space of the sound-generating box refers to the entire space or a portion thereof enclosed by the inner wall of the sound-generating box 1, which is used to contain air and allow sound waves to propagate and resonate therein.

[0024] The sound-generating element refers to the transducer that converts electrical signals into sound wave vibrations. Specifically, it can be implemented using an electromagnetic diaphragm or a piezoelectric ceramic element, and its function is to convert electrical signals into a basic sound source. The movable component 2 refers to a mechanical structure capable of changing its spatial form. Specifically, it can be implemented using hinged composite panels or flexible folding structures, changing the cavity volume and shape through displacement. The sound-generating box 1 refers to the shell structure that houses the sound-generating element and provides acoustic resonance space. Specifically, it can adopt a modular design, and its internal spatial form is controlled by the displacement of the movable component 2.

[0025] Specifically, the sound waves generated by the sound-producing element form standing waves within the cavity. The displacement of the movable component 2 alters the cavity's geometric parameters, thereby adjusting the resonant frequency characteristics. When simulating the pronunciation of different phonemes, the position of the movable component 2 is controlled to match the cavity shape with the oral cavity configuration corresponding to the target phoneme, making the sound production process more natural in both visual and auditory effects. For example, when producing closed vowels, the movable component 2 moves inward to reduce the cavity volume, simulating the acoustic environment when the jaw is closed.

[0026] In some embodiments, the sound-generating element is disposed within a sound-generating box 1 having a movable member 2, the movable member 2 being used to change the shape of the internal space of the sound-generating box 1, one end of the sound-generating box being openable and closable, and the sound-generating box being constructed to mimic the shape of the human oral cavity.

[0027] In some embodiments, the sound-generating box includes an openable and closable end, and the sound-generating element is disposed at the end of the sound-generating box opposite to the openable and closable end.

[0028] Compared to existing technologies, traditional devices typically use fixed cavities, resulting in fixed vowel resonant peaks and an inability to distinguish similar phonemes. This solution, through the dynamic adjustment of the movable component 2, allows the cavity shape to match the acoustic requirements of different phonemes in real time. For example, the first resonant peak frequency can be adjusted by changing the depth of the front cavity, and the high-frequency attenuation characteristics can be changed by adjusting the opening width.

[0029] Through the above technical solution, this application achieves dynamic simulation of oral cavity morphology, which can effectively improve vowel differentiation and the clarity of consonant plosives. Controllable changes in cavity volume make phoneme transitions more natural and accurately reproduce the acoustic differences between rounded and unrounded consonants. Motion control of the movable component 2 creates conditions for the generation of complex speech features.

[0030] This application further proposes that the interior of the sound-generating box 1 is configured to mimic the shape of the inside of the human oral cavity, and the side of the movable member 2 facing the inside of the sound-generating box 1 mimics the shape of the inner wall of the human mandible; the sound-generating box also includes a fixed member opposite to the movable member, for forming a stable resonant cavity reference surface.

[0031] Specifically, one method of mimicking the shape of the human oral cavity is to use 3D printing technology to construct the internal cavity of the sound box 1 into a structure with tooth arrangement, tongue space and hard palate contour.

[0032] Among them, the inner side of the movable component 2 imitates the shape of the inner wall of the human mandible, which means that the inner surface of the wall plate presents the arc-shaped concave feature of the inner side of the mandible. Specifically, it can be achieved by injection molding or 3D printing using medical-grade silicone material. When the wall plate moves, this structure can form a resonant cavity shape change that matches the actual opening and closing movements of the mandible.

[0033] Specifically, when the wall panel is closed, a gas channel similar to that of a human with a closed mouth is formed at the front of the cavity; when the wall panel is opened, the space at the front of the cavity expands to form a resonance cavity structure similar to that of an open vowel. This dynamic adjustment mechanism allows the shape of the resonance cavity to change according to the phoneme type.

[0034] Compared with existing technologies, traditional sound-generating devices use fixed rectangular or cylindrical cavities, which cannot simulate the effect of mandibular movement on the volume of the resonance cavity. This application constructs a biomimetic oral cavity structure with anatomical features, so that the movement trajectory of the movable component 2 is synchronized with the actual opening and closing angle of the mandible, thus achieving precise control over the shape of the oral cavity resonance cavity.

[0035] Through the above technical solution, this application solves the problem that static cavities lack a sense of realism in sound production due to the lack of dynamic resonance, enabling the sound-producing device to dynamically adjust the shape of the cavity opening through the movable component 2, and significantly improving the acoustic feature differentiation of vowels such as / i / and / u / .

[0036] In some embodiments, the movable member 2 is connected to the fixed member, and the inner curved surface of the fixed member is set to the curved surface of the human palate. Because the inner curved surface is set to the curved surface of the human palate, the shape of the resonance cavity is more in line with the actual human situation, and the sound production is more natural.

[0037] Among them, the movable component 2 refers to a movable cavity structure component, which can be implemented by means of hinge or slide rail connection, and is used to change the internal spatial shape of the sound box 1.

[0038] Among them, the fixed component refers to the cavity structure component with a fixed position. Specifically, it can be made of medical nanomaterials through injection molding or medical-grade nanomaterials through 3D printing. Its inner curved surface is designed with an arc consistent with the human upper jaw anatomy to form a stable, anthropomorphic airflow guide surface.

[0039] This application further proposes a biomimetic oral cavity sound-generating device. The sound-generating box 1 is designed to mimic the shape of the human oral cavity. One end of the sound-generating box 1 is an openable and closable end. The sound-generating element is located at the end of the sound-generating box 1 away from the openable and closable end, so as to simulate the process of human throat sound generation and sound wave transmission to the lips, making the sound generation more natural.

[0040] Among them, imitating the shape of the human oral cavity means that the overall structural outline of the sound box 1 matches the three-dimensional shape of the cavity inside the human oral cavity. Specifically, it can be achieved by using three-dimensional scanning data modeling combined with surface fitting technology, so that the reflection path of sound waves in the cavity is close to the real physiological structure.

[0041] The openable end refers to the end that has a controllable opening and closing function. Specifically, it can be achieved by using a hinged mechanical structure in conjunction with an electric push rod or a servo motor, and by adjusting the opening angle to simulate the lip closing action.

[0042] This application further proposes a bionic oral cavity sound-generating device, wherein the sound-generating box 1 includes a first sound-generating cavity and a second sound-generating cavity. The first sound-generating cavity is a cavity with a fixed volume, and the sound-generating element is disposed in the first sound-generating cavity. The second sound-generating cavity is disposed adjacent to the first sound-generating cavity, and the movable component 2 is disposed in the second sound-generating cavity.

[0043] The first sound-generating cavity refers to a resonant space with a stable internal volume, which can be implemented using a sealed chamber made of rigid material to stabilize the fundamental frequency of the sound waves generated by the sound-generating element. The second sound-generating cavity refers to a dynamically adjustable space adjacent to the first sound-generating cavity, which can be formed by separating it from the first sound-generating cavity through a flexible diaphragm or a rigid partition. In some embodiments, the first and second sound-generating cavities can also be fluidly connected, and their shape changes are controlled by the displacement of the movable component 2. The fixed volume refers to the internal space of the cavity remaining constant during sound generation, which can be achieved through a rigid cavity wall combined with a sealing structure to ensure that the basic acoustic characteristics are not disturbed. The movable component 2 refers to a mechanical structure that can change the spatial shape, which can be a biomimetic mandible model driven by a servo motor, achieving three-dimensional displacement through linear guide rails or opening and closing through a joint structure.

[0044] Specifically, a fixed-volume first sound cavity contains a built-in sound-generating element that produces a reference sound wave. The adjacent second sound cavity changes its shape through the displacement of the movable component 2. When the movable component 2 moves in a controlled manner, the volume change of the second sound cavity and the fixed volume of the first sound cavity create a composite acoustic effect. This compartmentalized structure allows the basic sound wave to maintain stable frequency characteristics within the fixed cavity, while simultaneously modulating the sound wave secondaryly through the shape changes of the dynamic cavities. For example, the forward and backward displacement of the movable component 2 can simulate the opening and closing of the mandible, and the left and right swinging can simulate the movement of the oral cavity lateral walls, thereby creating a composite resonance effect that matches the human vocalization process.

[0045] Compared to existing technologies, traditional bionic sound-generating devices, which use a single fixed cavity, cannot achieve dynamic adjustment of acoustic characteristics. This solution decouples stable sound generation from dynamic modulation through a split-cavity design. While maintaining the quality of the basic sound waves, it achieves precise adjustment of acoustic characteristics by independently controlling the shape of the second sound cavity. In existing technologies, the static cavity results in fixed vowel resonant peaks, while this solution can dynamically adjust the resonant peak frequency distribution by changing the geometric parameters of the second sound cavity through the movable component 2.

[0046] Through the above technical solution, this application achieves precise control of the resonance cavity morphology during sound production, effectively improving the adjustable range of vowel formants. The morphological adjustment of the second vocal cavity by the movable component 2 can simulate the influence of mandibular movement on oral cavity volume, making the generated speech exhibit more significant differentiation in phoneme features such as rounded and unrounded consonants. The design of the cavity-splitting structure also reduces interference with the fundamental frequency during sound wave modulation, ensuring the clarity of transient acoustic features such as consonant plosives.

[0047] This application further proposes a bionic oral cavity sound-generating device, including a sound-generating box 1, which includes a first side and a second side opposite to each other. The first side includes a movable member 2, and the second side is disposed adjacent to a second sound-generating cavity, which has an opening.

[0048] The first side refers to the side of the sound-generating box 1 where the movable component 2 is installed. This can be achieved using a movable, flexible material plate. The movable component 2 changes position mechanically to simulate jaw movement. The second side refers to the side opposite the first side, and can be separated by a perforated or non-perforated partition. When a through-hole is present, it forms a gas flow channel with the second sound-generating cavity. The second sound-generating cavity is an additional cavity connected to the second side. This can be achieved using a curved pipe mimicking a nasal cavity structure, with the opening at the end of the pipe to simulate the nostrils or the back of the mouth.

[0049] Specifically, when the movable component 2 is driven to move, the spatial shape of the first side changes, causing the airflow to redistribute inside the sound-generating box 1. The connection between the second side and the second sound-generating cavity allows some airflow to enter the second sound-generating cavity, and the existence of the opening allows the airflow to interact with the external environment. When producing a nasal sound, the movable component 2 can be closed, and a unique sound effect is produced through the resonance between the second sound-generating cavity and the sound-generating box 1.

[0050] Compared to existing technologies, traditional solutions only use a single fixed cavity, failing to achieve dynamic coupling between multiple cavities. This solution utilizes a fluid-connected second sound-emitting cavity, enabling the main cavity and the additional cavity to form a coordinated vibration system. When speech requires nasal involvement, the additional cavity can effectively enhance the sound wave energy at specific frequencies.

[0051] Through the above technical solution, this application achieves the coordinated vocalization function of the oral and nasal cavities. When producing nasal sounds, it can accurately simulate the physiological process of soft palate descent and airflow diversion, significantly improving the recognizability of nasal consonants. At the same time, the design of the open structure makes the airflow direction closer to the actual human vocalization state, avoiding the speech distortion caused by airflow obstruction in traditional solutions.

[0052] This application further proposes that the sound box 1 includes a first sound cavity and a second sound cavity in fluid communication, the second sound cavity being configured in a nasal cavity shape.

[0053] Among them, the first and second sound chambers with fluid communication refer to the continuous space formed between the two chambers through the airflow channel. Specifically, flexible ducts or deformable connecting tubes can be used to achieve this, so that airflow can be transmitted between the chambers to simulate the synergistic effect of the resonating chambers.

[0054] The second vocal cavity is constructed in the shape of a nasal cavity, meaning that the internal spatial form of the cavity matches the anatomical structure of the human nasal cavity. Specifically, this can be achieved by constructing a curved surface using three-dimensional scanning data to simulate the nasal cavity resonance effect.

[0055] Specifically, the first vocal cavity serves as a basic resonating cavity, simulating oral cavity function, while the second vocal cavity forms a continuous airflow path with it through a pre-designed nasal cavity structure. When airflow enters the second vocal cavity from the first vocal cavity, the inner wall of the nasal cavity shape resonates and modulates the airflow at a specific frequency, thereby generating sound waves with nasal characteristics.

[0056] Compared to existing technologies, which only feature a single fixed cavity or lack an auxiliary cavity with a nasal cavity shape, the current technology cannot accurately simulate the nasal resonance effect required for nasal sounds. This solution achieves coordinated resonance between the oral and nasal cavities through a fluid-connected dual-cavity structure and a second vocal cavity with a nasal cavity shape, ensuring that the propagation path of sound waves in the dual cavities during nasal sound production is consistent with the actual human physiological structure.

[0057] This application further proposes that the movable component 2 is installed to the sound-generating box 1 via a movable connector, the movable component 2 is connected to the transmission mechanism 3, and the transmission mechanism 3 is connected to the power source.

[0058] The movable connector refers to the mechanical connection device that enables relative movement between the movable component 2 and the sound-generating box 1. Specifically, it can be implemented using a hinge mechanism or a slide rail structure, allowing the movable component 2 to rotate or translate within a plane. The transmission mechanism 3 refers to the conversion device that transforms the power source output into mechanical motion. Specifically, it can be implemented using a motor-driven linkage mechanism or a rack and pinion mechanism, used to precisely control the displacement trajectory of the movable component 2. The power source refers to the energy supply device that drives the transmission mechanism 3. Specifically, it can be implemented using a servo motor or a linear motor, capable of outputting driving force in different directions according to the control signal.

[0059] Specifically, the rotational or linear motion output by the power source through the transmission mechanism 3 is converted into a composite motion trajectory of the movable component 2 via the movable connector. Driven by the power, the movable component 2 can open and close along a preset path, for example, simulating the vertical opening and closing motion of the human mandible, while simultaneously achieving continuous changes in the oral cavity volume through lateral displacement. The reduction gear in the transmission mechanism 3 can adjust the movement speed, allowing the movable component 2 to achieve a gradual morphological adjustment between the closed state and the maximum open state.

[0060] Compared with existing technologies, traditional bionic sound-generating devices use fixed wall panels or single-degree-of-freedom motion structures, which cannot achieve multi-dimensional cavity shape adjustment. In some embodiments, through the combined design of movable connectors and transmission mechanism 3, the movable component 2 has the ability to perform complex motion in three-dimensional space, such as having 3-6 or even more degrees of freedom, which can accurately reproduce the lateral displacement characteristics accompanying the opening and closing of the human mandible, thereby more realistically simulating the dynamic changes in oral cavity shape.

[0061] Through the above technical solution, this application achieves real-time dynamic control of the vocal cavity shape, solving the problem of missing speech features caused by the fixed cavity shape in the prior art. By precisely controlling the movement trajectory of the movable component 2, the cavity shape required for the pronunciation of different phonemes can be accurately simulated. In particular, for vowel conversion processes that require multi-directional jaw movement, the naturalness and phoneme differentiation of the speech output are effectively improved.

[0062] In some embodiments, the movable member 2 is connected to the transmission mechanism 3; the movable member 2 is configured to simulate the movement of human lips, and the transmission mechanism 3 is used to drive the movable member 2 to move in multiple directions.

[0063] In some embodiments, the movable component 2 refers to a movable structural part disposed inside the sound-generating box 1. Specifically, it can be implemented using a flexible polymer material composite rigid support frame, or medical nanomaterials through 3D printing, with its surface morphology designed to match the geometric shape of human lip movement. The transmission mechanism 3 refers to a drive device that converts power into mechanical displacement. Specifically, it can be implemented using a micro servo motor in conjunction with a multi-axis linkage mechanism. By controlling the rotation angle and speed of the motor, the movable component 2 can achieve compound movement in the vertical, horizontal, and inclined directions.

[0064] Specifically, after receiving motion commands from the control system, the transmission mechanism 3 drives the movable component 2 to perform spatial displacement through multi-axis linkage. The opening and closing motion of the movable component 2 in the vertical direction can be used to simulate the rising and falling motion of the human jaw, the extension and retraction motion in the horizontal direction can be used to simulate the opening and closing motion of the lips, and the tilting and oscillating motion simulates the dynamic process of the tongue contacting the hard palate during pronunciation. This multi-degree-of-freedom motion mode allows the internal spatial shape of the sound box 1 to respond in real time to the pronunciation needs of different phonemes. For example, when generating closed vowels, the movable component 2 is driven to close quickly to form a closed cavity, and when generating rounded vowels, the movable component 2 is driven to form a ring-shaped contraction state.

[0065] Compared to existing technologies, traditional bionic sound-generating devices rely solely on unidirectional movement for cavity shape adjustment, failing to replicate the complex movements of the human lips during vocalization. This solution uses a transmission mechanism 3 to drive the movable component 2 in three-dimensional space, making the shape changes of the oral resonance cavity more closely resemble the real physiological process. This is particularly effective when processing continuous phonemes that require coordinated lip shape changes, enabling smoother shape transitions.

[0066] Through the above technical solution, this application can accurately control the dynamic deformation process of the sound cavity, effectively improve the distinguishability of vowel formant frequencies, and improve the clarity of consonant plosives.

[0067] In some embodiments, the biomimetic oral cavity sound-generating device includes a sound-generating box 1 comprising an opening configured to include the shape of human lips, and a movable member 2 connected to the opening.

[0068] In some embodiments, the movable member 2 is connected to a transmission mechanism; the movable member 2 is configured to simulate the movement of human lips, and the transmission mechanism is used to drive the movable member to move in multiple directions.

[0069] In some embodiments, the transmission mechanism 3 is a set of linkage mechanisms, including a first link 31, a second link 32, and a third link 33; the first link 31 is connected to a power source (not shown in the figure) through a first rotating connector 311, and the power source drives the first link 31 to swing within a certain angle range; the second link 32 is rotatably connected to the first link 31 through a second rotating connector 321, and the second link 32 is rotatably connected to the third link 33 through a third rotating connector 331; the third link 33 is rotatably connected to the robot's fixed part or to the fixed component of the sound box, and the movable component 2 is rotatably connected to the fixed component through a fourth rotating connector 332.

[0070] In some embodiments, the opening shape of the human lips refers to the opening structure provided at the front end of the sound box 1. Its contour and curvature match the shape of the human lips in a naturally closed or slightly open state. Specifically, it can be made of flexible silicone material through molding or medical-grade nanomaterials through 3D printing technology. The shape of the opening directly affects the vibration mode when airflow passes through.

[0071] The connection between the movable component 2 and the opening means that the movable component 2 forms a linkage structure with the edge of the opening through a mechanical connector or elastic material. Specifically, it can be achieved by using a hinge mechanism or a linear guide rail. The displacement of the movable component 2 can cause the edge of the opening to deform, thereby adjusting the degree of closure and the outward angle of the opening.

[0072] Specifically, the opening is constructed in the shape of human lips, with its inner edge connected to the moving end of the movable component 2 via an elastic material. When the movable component 2 is driven by the transmission mechanism 3 to generate displacement, the lateral width and longitudinal opening angle of the opening change accordingly. For example, when producing closed vowels, the movable component 2 causes the opening edge to contract inward to form a closed state, while when producing rounded vowels, the movable component 2 drives the opening edge to bulge outward to form a ring-shaped contraction structure. Thus, the dynamic adjustment of the opening shape can simulate the muscle movement of human lips during pronunciation, allowing airflow to produce acoustic characteristics closer to real pronunciation when passing through the opening.

[0073] In some embodiments, the sound box is configured to mimic the acoustic characteristics of the human throat and / or oral cavity.

[0074] Compared to existing technologies, the opening structure of current bionic voice-generating devices typically uses a fixed shape, which cannot achieve precise dynamic adjustment of the lip shape, resulting in insufficient acoustic differentiation between closed and rounded consonants. This solution, through the linkage structure between the movable component 2 and the opening, enables the opening to change its shape simultaneously in multiple directions, such as adjusting the lateral contraction and longitudinal protrusion of the opening at the same time, thereby more accurately reproducing the complex movement pattern of the human lip during pronunciation.

[0075] In some embodiments, the spatial volume of the sound box is used to control the tongue position height characteristics of vowels; the mandibular opening parameter; and the lip shape control parameter: used to control the opening shape and size of the sound box outlet to achieve a spread lip or rounded lip shape.

[0076] This application also provides a robot that includes any of the above-described bionic oral speech devices.

[0077] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A biomimetic oral cavity sound-generating device, characterized in that: The device includes a sound-generating element disposed within a sound-generating box. The sound-generating box includes a movable component that changes the shape of the internal space of the sound-generating box. One end of the sound-generating box is openable and closable. The sound-generating box is constructed to mimic the shape of a human mouth. The movable component is connected to a transmission mechanism and is configured to simulate the movement of human lips. The transmission mechanism drives the movable component to move in multiple directions.

2. The bionic oral cavity sound-generating device according to claim 1, characterized in that: The movable component is configured to simulate the movement of the human lips, and the movable component is made of an elastic material.

3. The bionic oral cavity sound-generating device according to claim 1, characterized in that: It also includes a fixed component; the movable component facing inwards from the sound-generating box is shaped like the inner wall of the human mandible; the movable component is connected to the fixed component.

4. The bionic oral cavity sound-generating device according to claim 1, characterized in that: The sound-emitting box includes a first side and a second side opposite to each other. The first side includes the movable member. The sound-emitting box also includes a second sound cavity. The second side is disposed adjacent to the second sound cavity. The second sound cavity has an opening. The second sound cavity is constructed in the shape of a nasal cavity.

5. The bionic oral cavity sound-generating device according to claim 1, characterized in that: The movable component is installed to the sound-generating box via a movable connector, and the transmission mechanism is connected to the power source.

6. The bionic oral cavity sound-generating device according to claim 1, characterized in that: The sound-generating box is constructed to simulate the acoustic characteristics of the human throat and / or oral cavity.

7. The bionic oral cavity sound-generating device according to claim 1, characterized in that: There are multiple movable components, and the multiple movable components are connected to each other by connectors.

8. A robot, characterized in that, Includes the bionic oral cavity sound-producing device as described in any one of claims 1-7.

Images