PORTABLE WIRELESS VOICE MONITORING SYSTEM

Abstract

A portable wireless voice monitoring system in the form of a collar is disclosed, which allows monitoring of voice usage under everyday conditions, through autonomous operation, and at the same time maintains the accuracy and integrity of the signals obtained; the system comprises: a sensor device comprising sound monitoring means and an accelerometer that records sound signals and acceleration variations on the skin of a user; a control device in electrical communication with the sensor device, the control device comprising processing means and data transmission means; wherein the control device is configured to receive and process the signals obtained by the sensor device and to transmit the processed data to an external location.

Description

This application claims benefit from the Applicants' earlier provisional application, number US 63 / 061.348, filed on August 5, 2020. BACKGROUND OF THE INVENTION The voice is a fundamental tool in people's lives, as communication is primarily determined by it. Therefore, the appearance of voice conditions or disorders that affect or eliminate the ability to speak represents a significant decrease in quality of life and a serious occupational health problem. Vocal cord nodules, muscular dysphonia, tension, spasmodic dysphonia, vocal cord paralysis, and temporary loss of voice, among others, affect millions of people worldwide each year. Currently, treatments for voice disorders are only conducted through medical consultations and are limited to short visits, which does not allow for the collection of consistent and sufficient information to accurately describe everyday voice use. In this regard, clinical monitoring is essential for the effective diagnosis and treatment of these disorders, but its implementation is restricted to medical consultations, thus precluding the collection of information that accurately reflects actual voice use. Without this information, specialists can only design broad-spectrum therapies, which are often ineffective and lead to a high rate of recurrence. Recently, to provide adequate monitoring of patients with voice disorders, wearable devices, usually in the form of necklaces, have been developed that allow monitoring of voice use by means of electrodes, microphones and other equipment. An exemplary prior art technology is described in US patent 2014 / 235977 A1, which discloses a neck-worn sensor that is a unique body-worn system for measuring several parameters of an outpatient. From stroke volume, a first algorithm employing a linear model can estimate the patient's pulse pressure. From pulse pressure and pulse transit time, a second algorithm, also employing a linear model, can estimate systolic and diastolic blood pressure. Thus, the collar can measure all five vital signs along with hemodynamic parameters. It also includes a motion-detecting accelerometer, from which IVIA / t / ZUZÓ / UZO I lf can determine movement-related parameters such as posture, degree of movement, activity level, breathing-induced chest agitation, and falls. The device described above addresses the portability issues, enabling semi-continuous user monitoring via a handheld device. However, this device is designed for general data recording, without requiring special attention to signal integrity. This is evident from the purpose of the transducer used—an accelerometer—which is intended to record user movement, but lacks post-processing for in-depth analysis of the voice signal characteristics. Another approach to recording and analyzing voice signals relies on the use of accelerometers on the surface of the neck, which allow for non-invasive and non-obstructive measurements of speech and swallowing. A representative document of this type of prior art technology is US patent 2014 / 0066724 A1, which describes a system and method for evaluating an individual's vocal function. This system includes an accelerometer configured to acquire surface acceleration data associated with the individual's vocal function and a computer system configured to analyze the surface acceleration data and estimate glottal airflow waveforms produced by the individual, based on the surface acceleration data.The computer system performs the analysis and estimation by applying an inverse filter to the surface acceleration data, based on a calibrated transmission line model, and generates an indication of the individual's vocal functionality, based on the estimated glottal airflow waveforms. However, the described system requires connecting a sensor to a computer system to analyze the data it collects. Consequently, the system does not address portability issues and is not suitable for standalone operation. Furthermore, the computer system requires audio codecs to pre-process and digitally store the data. This pre-processing can vary depending on the computer system and may include gain, bandpass filtering, and noise reduction, all of which can distort the signal, affecting signal integrity and subsequent data analysis. Additionally, as a wired device, it is prone to unintentional connection problems. Consequently, there is a need to provide a self-contained device to record the full use of the voice during the day, under everyday conditions, and that is capable of maintaining -at the same time- the accuracy and integrity of the signal, so that the data can be used to obtain and estimate certain parameters and indicators that are useful for the evaluation of vocal function. BRIEF DESCRIPTION OF THE INVENTION The invention relates to a portable wireless voice monitoring system, in the form of a collar, which allows monitoring of a user's voice usage, wherein the system comprises: a sensor device comprising sound monitoring means and an accelerometer that records sound signals and acceleration variations in a user's skin; and a control device in electrical communication with the sensor device; wherein the control device comprises processing means and data transmission means; where the control device is configured to receive and process the signals obtained by the sensor device and transmit the processed data to an external location. The described system comprises compact, small components that allow for portability and use as a portable device, thus enabling continuous voice monitoring under everyday conditions. Through the combined use of sound monitoring devices and an accelerometer, the system is able to accurately record and analyze vocal cord usage, estimating a range of physiological parameters that are of clinical interest not only to researchers and voice professionals, but also to any professional who uses their voice as a work tool and requires precise monitoring of their vocal health, such as broadcasters, singers, teachers, journalists, and others.Thus, the specific configuration of the described system is able to substantially improve the capacity for evaluation, diagnosis and monitoring of vocal pathologies that affect millions of people a year worldwide and that, in their most serious cases, can even lead to permanent loss of voice. Therefore, the operation of the device of the present invention is based on the use of an accelerometer and a microphone simultaneously, which allows real-time signal processing to deliver instant feedback to users, based on their vocal use, which constitutes a disruptive methodology for vocal therapies. One of the key features of the described system is that the processing means are separate from the sensor device, thus providing separate, small, and compact elements that facilitate portability and user comfort by providing a minimally invasive, wearable device in the form of a collar. Preferably, the processed data obtained from the captured signals can be stored on a data storage medium in the control device and transmitted, periodically or in real time, to an external location, such as an external computer or the cloud, where it can be subsequently analyzed by a specialist for further processing or medical analysis. Alternatively, the control device can be configured to transmit information in real time to a user interface, such as a smartphone app, via Bluetooth. One of the key aspects addressed by the invention is signal integrity. This is achieved, firstly, by selecting the correct transducers—an accelerometer with the specific bandwidth for vocal applications combined with a microphone—and secondly, through the optimal data acquisition process, which includes hardware filtering to pre-condition the signal and then the use of an audio codec for further signal processing. The combination of these features of the invention provides complete control over the behavior of the input signal, minimizing harmonic and phase distortions and ultimately encoding the data for transfer and storage. Specifically, the use of an accelerometer strategically placed in the trachea allows for the estimation of glottal flow, subglottic pressure, and other variables crucial for identifying vocal hyperfunction. Additionally, the data obtained by the accelerometer is complemented by ambient sound recording from sound detectors, which can be selectively switched on and off, allowing the patient to decide when they do not want certain information recorded. The combination of both mechanisms enables the instantaneous monitoring of vocal abuse. The combined and simultaneous use of two types of signals—sound and acceleration—allows for the delivery of clinically relevant information for vocal function assessment and has proven to better identify patterns of vocal abuse, resulting in a more useful device and, therefore, greater appreciation from healthcare professionals and patients. Its features enable feedback through advanced parameters and indicators for vocal use, representing a revolutionary therapeutic methodology by pre-processing the signals and transmitting data to provide feedback to the user. Furthermore, its wireless, ergonomic, and discreet design conceals its medical nature and facilitates its use, resulting in an object that does not appear to be a medical device. This allows the user to use the device as a portable item without affecting the quality of the captured signals. BRIEF DESCRIPTION OF THE DRAWINGS Figures 1A and 1B illustrate preferred embodiments of the portable wireless voice monitoring system of the present invention. MA t ZUZO UZO ilf Figure 2 illustrates a detailed view of the sensor device, in a preferred embodiment of the invention. Figure 3 illustrates a detailed view of the control device, in a preferred embodiment of the invention. DETAILED DESCRIPTION OF THE INVENTION The following are detailed descriptions of some exemplary embodiments to illustrate the principles of the invention. These embodiments are provided to illustrate aspects of the invention, but the invention is not limited to any one embodiment. The scope of the invention encompasses numerous alternatives, modifications, and equivalents, limited only by the embodiments in the claims. According to Figures 1A, 1B and 2, in a first aspect of the invention a portable wireless voice monitoring system (100) in the form of a collar is disclosed, comprising: a sensor device (110) comprising sound monitoring means (112) and an accelerometer (114) that records sound signals and acceleration variations in a user's skin; a control device (120) in electrical communication with the sensing device (110), wherein the control device comprises processing means and data transmission means; where the control device is configured to receive and process the signals obtained by the sensor device and to transmit the processed data to an external location. As shown in Figures 1A and 1B, the control device and the sensor device are preferably connected by an electrical link (130), which enables communication between them. This allows the signals captured by the sensor device (110) to be transferred to the control device (120) for processing. This configuration of separate elements results in small and compact sensor and control devices, thus providing a comfortable and non-invasive system for the user. Preferably, the system (100) is configured to position the control device (120) on the back of the neck and the sensor device (110) on the forehead, near the trachea. Preferably, the sensor device (110) is positioned on the skin of the neck, between the sternal notch and the thyroid prominence, to allow for more precise signal reception. With reference to Figure 2, a detailed view of a preferred embodiment of the sensor device (110) is revealed. In this embodiment, the sensor device (110) comprises a front housing (111), sound monitoring means (112), an accelerometer housing (113), the accelerometer (114), a back cover (115), adhesive means (117), and a rubber or silicone pad (116). The front housing (111) and the back cover (115) are configured to interlock and provide housing for the sound monitoring means (112) and the accelerometer (114). The back cover (115) may include an opening (118) to allow communication between the accelerometer (114) and the user's skin. The adhesive means (117) are configured to allow removable attachment of the sensor device (110) to the user's skin, preferably by means of double-sided tape.Additionally, the elements of the sensor device are preferably designed and selected so as not to affect the capture of signals, especially the back cover (115), the rubber pad (116) and the adhesive means (117), where the adhesive means (117) must allow a fixation capable of allowing the transmission of vibrations for the correct functioning of the accelerometer. With reference to Figure 3, a detailed view of a preferred embodiment of the control device (120) is shown. In this embodiment, the control device (120) comprises control means (121), a front housing (122), processing means (123), energy storage means (124), and a rear cover (125). The control means (121) is configured to include one or more buttons to enable control of certain operating features of the system. Preferably, the energy storage means (124) is configured to provide a lifetime of more than 12 hours of continuous recording, thereby enabling uninterrupted monitoring throughout the day and obtaining measurements over several days. The energy storage means (124) enable autonomous operation of the system. To achieve this operation, the energy storage means (124) preferably consist of a battery that allows the system to function without a physical connection to an external power source. In this configuration, a charging port may be included in the control device to allow the battery to be charged from an external source. The processing means (123) are configured to implement speech processing algorithms and control all elements of the system (100). Preferably, the processing means (123) consists of a printed circuit board configured with state-of-the-art electronic technology and is capable of processing signals to deliver instant feedback (biofeedback) to users based on their vocal usage, representing a new methodology for voice therapies. The data obtained can be securely stored and processed in the cloud (HIPAA compliant) or at an external location, thanks to unique algorithms specifically designed for interpreting this data, enabling the generation of new information useful to healthcare professionals (such as the flow). IVIA / t / ZUZÓ / UZO I lf glottic airway, subglottic pressure and vocal efficiency). In preferred embodiments of the invention, the processing means (123) include data storage means configured to store all data being processed by the system, thereby enabling data processing while the device is in use. The control device preferably includes data transmission means configured to allow the transmission of processed data to an external location. Preferably, the transmission means are configured to transmit the processed data, periodically or in real time, to an external location, such as an external computer or the cloud, where it can be subsequently analyzed by a specialist for further processing or medical analysis. Alternatively, the control device can be configured to transmit information in real time to a user interface, such as a computer or a smartphone application, via Bluetooth. In preferred modalities, the processed data is transmitted, preferably, to a user interface configured to display and analyze the data in corresponding software, aimed at researchers and voice professionals. The processed data can be viewed on all types of mobile platforms and computers, for both healthcare professionals and patients, to visualize and analyze the processed information periodically or in real time, and to monitor vocal function in unprecedented ways. The control means (121) may consist of a keypad that includes one or more buttons, or may be configured as a touchpad, and are configured to provide basic commands for system operation, such as turning the system on and off or other alternative functions. In addition, the control means may include display means, such as a screen or lights, to provide basic information about the operating status, such as battery level or other operating characteristics. In preferred configurations, the processing equipment is set up to apply various treatments or algorithms to the input signal, including hardware filtering for pre-conditioning and then the use of an audio codec for further signal processing. This procedure, combined with the use of appropriate transducers, an accelerometer with bandwidth specifically designed for vocal applications, and a microphone, ensures signal integrity, providing complete control over the input signal's behavior, minimizing phase and harmonic distortion, and ultimately encoding the data for transfer and storage. The processing means are configured to implement a speech analysis engine, which is the core of the analysis obtained by the system (100). The analysis engine MA t ZUZO UZO ilf vocal comprises several algorithms designed for the evaluation of vocal function, with two analysis modules that work with a neck surface acceleration (ACC) signal and a sound signal obtained by sound monitoring means, preferably a microphone (MIC). The first analysis module is the standard vocal health analysis, which considers vocal signal processing approaches not available in any previous ambulatory voice monitor. This module includes the following functions: - MIC signal de-intelligibility, in which the large bandwidth signal is transformed into selected features, such as SPL (sound pressure level) using MIC RMS (root mean square), FFT (Fast Fourier Transform) magnitude; - daily verification of the ACC placement calibration, which is performed using MIC RMS and ACC data after VAD (vocal activity monitoring); - robust monitoring of vocal activity (VAD) in the ACC signal and related VAD features, using ACC and MIC correlation; - vocal intensity that is performed using MIC RMS and ACC data after VAD; - fundamental frequency (fO), from the ACC signal by autocorrelation; - vocal dose (SPL and fO of the ACC signal) including cycle and distance dose; - acoustic dosimeter, which includes monitoring of the background noise level by processing VAD and MIC signals; - vocal efficiency (SPL vs ACC); - H1-H2, relationship between the first and second harmonic, FFT basis of the ACC signal; - spectral tilting, high-resolution filtering in the FFT of the ACC signal; - CPP (cepstral peak prominence) in ACC and MIC signals. In addition, the processing devices can acquire the following advanced features, which have been shown to better identify hyperfunctional vocal behaviors and are key to a more comprehensive assessment of vocal function in an outpatient setting: - Aerodynamic characteristics such as AC flow (unsteady airflow), MFDR (maximum flow decline rate), OQ (opening quotient, ratio of opening period to full glottal cycle duration), SQ (velocity quotient, ratio of vocal fold opening to closing phase) obtained using the IBIF (impedance-based inverse filtering) algorithm from the ACC signal, OW (oral airflow volume velocity), and subglottic pressure. It also includes a calibration scheme to obtain robust, individual-specific IBIF parameters using MIC inverse filtering, instead of the OW (oral airflow volume velocity) signal (obtained using specialized equipment and in a controlled environment). MA t ZUZO UZO ilf controlled) in the original IBIF algorithm). The IBIF model parameters are obtained using a weighting method that combines information from the estimation of different vowels. This new calibration scheme had not been previously described in the scientific / technical literature; - Subglottic pressure is obtained by multivariate linear regression (using the previous aerodynamic characteristics, ACC and IBIF characteristics) using the SPL of the MIC signal; - monitoring singing using the ACC and MIC signals. Therefore, through the features described above, the invention allows for obtaining and estimating parameters and indicators useful for evaluating vocal function, such as SPL, VAD, fO, H1-H2, and CPP, which today can only be obtained in clinical settings, and some of them, such as aerodynamic characteristics, require highly invasive procedures for their acquisition. The voice monitoring system described herein allows for the continuous acquisition of these parameters and indicators using a portable device. Furthermore, the processing capabilities are configured to provide daily reports. Once the vocal health indicators are calculated, the voice analysis engine generates a summary of the results. These results are saved and sent to both users, for example, via a mobile application or web browser, and healthcare professionals. The specific content includes raw data, daily / weekly statistics, and a daily biofeedback summary. In addition to the daily reports, the Voice Analysis Engine can also generate graphical information based on the daily reports and user-requested analyses. The functions of this module can be selected as needed and include: - Spectral and waveform visualization over time, with user-defined time window; - Multiple vocal health measurements over time, with smoothing and user-defined time window; - one-dimensional and two-dimensional histograms for any of the standard or advanced vocal measures; - visualization using the UMAP dimensionality reduction technique; - comparison of parameters within the same time window, across different days of the analysis; - correlation of the alterations in the parameters obtained with the user's habits (smoking, eating, shouting, etc.) and environmental variables; - Obtaining indicators of vocal efficiency level, which correspond to indicators that describe voice quality. These indicators allow patients to notice their improvement; - estimation of parameters to identify and support the diagnosis of different 5 pathologies and / or health conditions, even beyond the voice, such as, for example, Parkinson's. Although the present invention has been described in terms of particular modalities and applications, both in summary and in detail, it is not intended that these descriptions in any way limit its scope to such modalities and applications, and it shall be understood that those skilled in the art may make many substitutions, changes, and variations in the modalities, applications, and details described of the methods and system illustrated herein, without departing from the spirit of the present invention.

Claims

1. A portable wireless voice monitoring system (100) in the form of a collar, characterized in that it comprises: a sensor device (110) comprising sound monitoring means (112) and an accelerometer (114) that records sound signals and acceleration variations on the skin of a user; a control device (120) in electrical communication with the sensor device (110), wherein the control device comprises processing means and data transmission means; wherein the control device is configured to receive and process the signals obtained by the sensor device and to transmit the processed data to an external location.

2. A portable wireless voice monitoring system, according to claim 1, characterized in that the control device and the sensor device are connected by an electrical connection (130) that allows the transfer of the signals captured by the sensor device (110) to the control device (120) for processing.

3. A portable wireless voice monitoring system, according to claim 1, characterized in that the control device (120) is located on the back of the neck and the sensor device (110) is located in the frontal area, near the trachea, to allow for more accurate reception of the signals.

4. A portable wireless voice monitoring system, according to claim 3, characterized in that the sensor device (110) is located on the skin of the neck between the sternal notch and the thyroid prominence.

5. A portable wireless voice monitoring system according to claim 1, characterized in that the sensor device (110) comprises sound monitoring means (112), an accelerometer housing (113), the accelerometer (114), a front housing (111) and a rear cover (115) configured to couple and provide a housing for the sensor device.

6. A portable wireless voice monitoring system according to claim 5, characterized in that the sensor device (110) further comprises adhesive means (117) configured to allow removable attachment of the sensor device (110) to the user's skin, and a rubber or silicone pad (116) selected so as not to affect the reception of signals.

7. A portable wireless voice monitoring system, according to claim 5, characterized in that the back cover (115) includes an opening (118) to allow communication between the accelerometer (114) and the user's skin.

8. A portable wireless voice monitoring system, according to claim 1, characterized in that the control device (120) comprises control means (121), a front housing (122), processing means (123), energy storage means (124) and a rear cover (125).

9. A portable wireless voice monitoring system, according to claim 8, characterized in that the control means (121) include one or more buttons to allow control of some operating features of the system.

10. A portable wireless voice monitoring system, according to claim 8, characterized in that the control means (121) include a keypad with one or more buttons or a touch panel and are configured to provide basic commands for the operation of the system, such as turning the system on and off, among others.

11. A portable wireless voice monitoring system, according to claim 8, characterized in that the control means include display means, such as a screen or lights, to provide basic information about the operating status, such as battery level, or other operating characteristics.

12. A portable wireless voice monitoring system, according to claim 8, characterized in that the energy storage means (124) are configured to provide autonomous operation of more than 12 hours of continuous recording.

13. A portable wireless voice monitoring system, according to claim 1, characterized in that the processing means (123) are configured to process and send the signals to an external location.

14. A portable wireless voice monitoring system, according to claim 1, characterized in that the processing means (123) include data storage means configured to store all data being processed by the system.

15. A portable wireless voice monitoring system, according to claim 1, characterized in that the transmission means are configured to transmit the processed data to the external location where it can be subsequently analyzed by a specialist, in further processing or medical analysis.

16. A portable wireless voice monitoring system, according to claim 15, characterized in that the processed data is transmitted, preferably, to a user interface, which is configured to display and analyze the data in corresponding software.

17. A portable wireless voice monitoring system according to claim 1, characterized in that the processing means are configured to implement treatments or algorithms to the input signal, including hardware filtering, to precondition the signal and then use an audio codec to further process the signals.

18. A portable wireless voice monitoring system according to claim 1, characterized in that the processing means are configured to implement a voice analysis engine, comprising algorithms designed for the evaluation of voice function, with an analysis module that operates with a neck surface acceleration (CSA) signal and a sound signal obtained by the sound monitoring means, preferably a microphone (MIC).

19. A portable wireless voice monitoring system according to claim 18, characterized in that the analysis module includes: - MIC signal de-intelligibility, wherein the high-bandwidth signal is transformed into selected features, such as SPL (sound pressure level) by means of MIC RMS (root mean square), FFT (Fast Fourier Transform) magnitude; - daily check of ACC placement calibration, which is performed via MIC RMS and ACC data after VAD (vocal activity monitoring); - robust monitoring of vocal activity (VAD) on the ACC signal and related VAD features, using ACC and MIC correlation; - vocal intensity, which is performed via MIC RMS and ACC data after VAD; - fundamental frequency (fO), from the ACC signal by means of autocorrelation; - vocal dose (SPL and fO of the ACC signal) including cycle and distance dose;- Acoustic dosimeter, which includes monitoring of the background noise level by processing VAD and MIC signals; - Vocal effectiveness (SPL vs ACC); - H1-H2, ratio between the first and second harmonics, H1 basis of the ACC signal; - Spectral slope, high-resolution filtering in the FFT of the ACC signal; - CPP (cepstral peak prominence) in the ACC and MIC signals.

20. A portable wireless voice monitoring system, according to claim 18, characterized in that the voice analysis engine further comprises advanced features intended to better identify hyperfunctional vocal behaviors, including: - aerodynamic features such as AC flow (unstable airflow), MFDR (maximum flow decline rate), OQ (opening quotient, ratio of the opening period to the duration of the complete glottal cycle), SQ (velocity quotient, ratio of the opening phase to the closing phase of the vocal folds) obtained by means of the IBIF (impedance-based inverse filtering) algorithm from the ACC signal, which includes a calibration scheme to obtain robust individual-specific IBIF parameters by means of MIC inverse filtering;- subglottic pressure obtained by multivariate linear regression (using previous aerodynamic characteristics, ACC and IBIF characteristics) using the SPL of the MIC signal; and edge monitoring using the ACC and MIC signals.; 21. A portable wireless voice monitoring system, according to claim 18, characterized in that the processing means are configured to provide daily reports, including data generated by the voice analysis engine, such as raw features, daily / weekly statistics, and daily biofeedback summary.

22. A portable wireless voice monitoring system according to claim 21, characterized in that the voice analysis engine is also capable of generating graphical information 5 based on daily reports and user-requested analyses, and providing a correlation between the obtained parameters and the user's habits and environmental characteristics, including: - spectral and waveform visualization over time, with a user-defined time window; - multiple vocal health measures over time, with smoothing and a user-defined time window; - one-dimensional and two-dimensional histograms 10 for any of the standard or advanced vocal measures; and - visualization using the UMAP dimensionality reduction technique; - comparison of parameters within the same time window, between different days of the analysis;- Correlation of alterations in the obtained parameters with the user's habits (smoking, eating, shouting, etc.) and environmental variables; - Obtaining indicators of the level of vocal efficiency, which correspond to 15 indicators that describe voice quality. These indicators allow patients to notice their improvement; estimation of parameters to identify and support the diagnosis of different pathologies and / or health conditions, even beyond the voice, such as Parkinson's disease.

Images