WO2020046098A1 - Système et dispositif sans fil et portable pour enregistrement, traitement et reproduction de sons chez des personnes présentant une dystrophie du système respiratoire - Google Patents

Système et dispositif sans fil et portable pour enregistrement, traitement et reproduction de sons chez des personnes présentant une dystrophie du système respiratoire Download PDF

Info

Publication number
WO2020046098A1
WO2020046098A1 PCT/MX2018/000079 MX2018000079W WO2020046098A1 WO 2020046098 A1 WO2020046098 A1 WO 2020046098A1 MX 2018000079 W MX2018000079 W MX 2018000079W WO 2020046098 A1 WO2020046098 A1 WO 2020046098A1
Authority
WO
WIPO (PCT)
Prior art keywords
processing
recording
dystrophy
reproduction
wireless
Prior art date
Application number
PCT/MX2018/000079
Other languages
English (en)
Spanish (es)
Inventor
Daniel ARAGÓN HAN
Yoku SASHIDA MÉNDEZ
Paulo César VÁZQUEZ ESTRADA
Abel AGUILAR CHÁVEZ
Original Assignee
Aragon Han Daniel
Sashida Mendez Yoku
Vazquez Estrada Paulo Cesar
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aragon Han Daniel, Sashida Mendez Yoku, Vazquez Estrada Paulo Cesar filed Critical Aragon Han Daniel
Publication of WO2020046098A1 publication Critical patent/WO2020046098A1/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/68—Operating or control means
    • A61F2/70—Operating or control means electrical
    • A61F2/72—Bioelectric control, e.g. myoelectric
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/003—Changing voice quality, e.g. pitch or formants
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation

Definitions

  • the present invention is related to the medical industry in general, and in particular relates to the field of medical devices; speech recovery and / or communication devices. More specifically it refers to a system integrated by a device and / or non-invasive device of the type of throat vibration, with microphones and wireless communication with a mobile platform and an external server and / or cloud. Which allows you to return the ability of oral communication to your user, by creating a less robotic and more human voice, as in cases that occur in dystrophies of the respiratory system, such as, without being limited to, a laryngotomy, total excision or partial larynx usually caused by the presence of cancer.
  • the larynx is the second most frequent site of upper aero-digestive tract cancer after the oral cavity.
  • the most common laryngeal cancer is squamous cell carcinoma (95% of all cases). This is more frequent in men. between 60 and 70 years of age, the risk factors are poor diet, HPV infection, genetic syndromes "Faconni anemia" but above all the history of cigarette and / or alcohol consumption, whose combination has been shown to potentiate the risk of generating this type of cancer.
  • Another associated factor occurs in workers exposed to substances such as paints, metals, plastics, fuels, among others.
  • the treatment involves surgery, known in the middle as, laryngectomy.
  • This surgery can be total or partial, it depends on the amount of larynx removed by the state of progress of the cancer.
  • the larynx is an organ of phonation and responds to the needs of the voice by containing the upper and lower vocal cords, so that its total or partial extraction directly affects the quality and possibility of oral communication of the patient.
  • the invention of document D1 and our invention have the following differences which demonstrates novelty for its implementation as a whole:
  • the invention of document D1 could only be used in healthy users in their speech ability.
  • the possibility is to be used in patients or users with dystrophy in the respiratory system and / or who have had partial and / or total laryngectomies, due to the form of implementation, position and information acquisition.
  • the invention of document D1 consists of a piezoelectric sensor mounted on an adjustable sailboat belt; which captures the vibrations in the user's throat and then transmits them, conditions, processes, filters and converts sounds without interference and echoes to other devices as a hands-free.
  • our invention integrates at one end of the collar, placed on the user's neck, a transducer that oscillates by vibrating the structure of the oral cavity and throat, supplying the absence of the vocal cords, consequently, sounds are obtained that, by movement of the mouth and tongue it is articulated in words returning to the user the ability to speak. While at the other end of the collar is a microphone that allows amplifying the conversation.
  • the invention of document D1 facilitates communication using, as a technological method, filters to keep the user's voice amplified without interference and transmitting it to other devices hands-free. Unlike our invention, which returns the ability to communicate to the user, allowing him to choose between different types of voice located and processed in the cloud, accessing through the internet.
  • the invention of document D2 Integrates three devices that condition the operation between them separately to be considered partially hands-free. Unlike our invention, which uses a maximum of two devices in combination and thus does not condition the use of the hands in its implementation, which is one of the biggest problems of users who use the invention of document D2.
  • the invention of document D2 conditions the amplification of the user's voice towards a loudspeaker.
  • an external module and / or interface such as an app or mobile device to reproduce, amplify and / or control other functions and with them access to the possibilities of the cloud for voice processing more human
  • the invention of document D2 can only generate in the user an artificial voice typical of an electronic larynx. Unlike our invention, it offers the possibility of an organic or closer to human voice between different options, accessing processes, methods of execution in the cloud such as the use of artificial intelligence algorithms, "machine learning” or “deep learning. " In this way, our invention solves the main problem of the Invention of D2 which is a robotic voice.
  • document D3 could only be used in healthy users in their speech ability. Unlike our invention, it is used in patients or users with dystrophy in the respiratory system allowing a more human voice through the implementation of artificial intelligence.
  • the invention of document D3 consists of a microphone transducer unit, composed of two piezoelectric elements mounted on a headband; which captures the vibrations in the user's throat and then transmits them, conditions, processes, filters and converts sounds without interference and echoes to a hearing aid placed at the other end of the headband.
  • a transducer that oscillates by vibrating the structure of the oral cavity and throat supplying the absence of the vocal cords, consequently, sounds are obtained, which by movement of the mouth and tongue is articulated in words returning to the user the ability to speak.
  • the end of the collar is a microphone that allows amplifying the conversation and sends the information to a web platform or interface and connects to the cloud, generating a more human voice.
  • the objective of the invention is to improve prior technologies to produce sounds without interference.
  • the features proposed in the invention of document D2 seek to return the ability to communicate partially hands-free and artificially verbally to the user.
  • the objective is to produce sound without interference and transmit them to a hearing aid of a sound user in his speech ability.
  • none of them solves the problem of generating a human voice by implementing cloud technology and artificial intelligence.
  • the present invention has as its main objective to make available a wireless and wearable system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system that allows to return the oral communication capacity to its user, by means of a voice less robotized in addition to adjusting the volume and frequency of the voice digitally.
  • Another object of the invention is to make available a novel and wearable wireless system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, which in addition said device is portable, light in weight less than (250 g), wearable and / or usable, below the average weights of esophageal or laryngeal speech devices such as electrolaringes and / or throat vibration type devices.
  • Another object of the invention is to make available a novel and wearable wireless system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, which also complements technologies of energy sources, signal acquisition, network connectivity local and external as cell phones, computers, servers.
  • Another objective of the invention is to make available a novel and wearable wireless system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, which also allows its user to implement it without using both hands, in a manner Ergonomic, with at least one speech intention detection system.
  • Another objective of the invention is to make available an innovative and wearable wireless system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, which also allows the information to be updated via the mobile platform and in conjunction with the server or cloud for improvements in the generation of a more human voice.
  • Another objective of the invention is to make available a novel and wearable wireless system and apparatus for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, which also allows to have a variety of voices applied through digital filters, where the User can customize their voice type, among different human options located in the cloud by accessing through the internet.
  • the system for recording, processing and producing sounds in people with dystrophy in the respiratory system in accordance with the present invention is made up of three interacting components that consist of a) a non-invasive wearable device of the throat vibration type (electrolaringe), with microphones and wireless communication, b) a mobile platform, and c) an external server / cloud.
  • Said non-invasive wearable device of the throat vibration type, with microphones and wireless communication has a sound source module; a signal acquisition module; a signal conditioning module; a logical processing and control module; an external power source; a wireless (connectivity) communication module with which said device connects to a local network and to the external server / cloud and interacting with the mobile platform.
  • Said sound energy source module consists of one or more of two multivibrator elements or oscillatory / vibratory transducers, which are placed directly on the patient's neck to create a sound energy source and are actuated by means of a pressure sensor and / or a button or switch and / or a muscle electrical activity detector.
  • the multivibrator elements are connected to an electronic power circuit for speed and intensity adjustment, which produces an adjustment in the tone and power of the sound energy source.
  • the electronic power circuit is connected directly to the signal processing and logic control module.
  • Said signal acquisition module consists of a plurality of microphones that define a network of microphones superimposed on the neck and close to the user's oral cavity which are directly connected to the signal conditioning module by means of metal cables. It is intended to capture the sound emitted by the sound source with the variations in energy, amplitude and frequency caused by the movement of the pharynx or throat. Said signals reach the signal conditioning module.
  • Said signal conditioning module is formed by an electronic circuit with a high impedance differential input; a preamp; a bandpass filter with the bandwidth adjusted according to the oscillation frequency of the multivibrator (high pass filter and low pass filter); finally an amplifier to obtain a signal limited in voltage and frequency and is fed from a power source.
  • This module connects directly to the logic control and processing module by means of metal tracks.
  • Said processing and logical control module allows obtaining information on the conditioned signal, processing and sending it, which is divided into four stages:
  • ADC stage conversion of the signal from the analog to digital conditioning stage and at the same time the internal and / or external memory information is stored.
  • Processing of the registered signal FIR and MR digital filtering (Finite Response Filters and Infinite Response Filters) are implemented to eliminate the parasitic frequencies produced by the multivibrator, then the information is packaged in blocks such as [a 11, a 12, ... to 1 n] of n-dimensions to be sent by the wireless communication module.
  • Connectivity control stage allows you to adjust the speed, and sending and receiving information of the device for setting device, algorithms, digital filters among others
  • the wireless communication module consists of a circuit, to mention, but not limited to a Bluetooth, wifi, in order to establish connection of the device with the mobile platform and transfer the information packets.
  • External power source it consists of an external power source such as a lithium battery with a voltage range of 1.8- 3.7 V which serves to power the different modules.
  • the mobile platform consists, but is not limited to a cell phone, Tablet and / or smartphones, with at least one type of wireless connection such as a Bluetooth, Wi-Fi and with speakers or sound reproduction systems where the device is processed and rebuilt.
  • temporal-spatial information processing techniques are implemented and selected as an example, but not limited to FFT, Wavelet Transform, etc. to achieve an effect of a digital equalizer
  • external / cloud servers are used where service calls are mainly used, subsequently the information is reproduced in the speakers or speakers of the mobile platform.
  • the platform connects to the server where updates are executed on the platform or filtered on the server.
  • the external server or cloud allows the interaction of the device and the platform with the external server for storage of information, optimization and adjustment of the algorithms of filtering and reconstruction of the voice. It is based on a computer system whose purpose is information storage, optimization and adjustment of the algorithms of filtering and reconstruction of the voice. Said server allows to store the pre-processed information and through optimization algorithms to seek to modify the FIR and IRR digital filters both in the device and in the mobile platform. Additionally, cloud services are used to improve the reproduction quality of the reconstruction of information.
  • Figure 1 illustrates the diagram of the wireless and wearable system and apparatus for recording, processing and reproduction of sounds in persons with dystrophy in the respiratory system, in accordance with the present invention.
  • Figure 2 illustrates a schematic diagram of the device and / or wearable non-invasive device of throat vibration type, with microphones and wireless communication, in accordance with the present invention.
  • Figure 3 illustrates the detailed schematic diagram of the wearable device and / or non-invasive vibration type device of throat, with microphones and wireless communication, in accordance with the present invention.
  • Figure 4 illustrates a conventional perspective of the non-invasive apparatus and set it for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, in accordance with the present invention.
  • Figure 5 shows a schematic representation with the device and / or non-invasive device and put it for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system, placed on the neck of a user.
  • Figure 6 shows a conventional perspective of a multi vibrating element or oscillatory / vibratory transducer for the generation of the sound source, of the non-invasive apparatus and set for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system.
  • Figure 6a illustrates a conventional perspective exploded of a mu Itivibrator or oscillatory / vibratory transducer element for the generation of the sound source, of the non-invasive apparatus and set for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system .
  • Figure 6b illustrates an exploded side view of a multivibrator element or oscillatory / vibratory transducer for the generation of the sound source, non-invasive apparatus and set for recording, processing and reproduction of sounds in people with dystrophy in the respiratory system.
  • Figure 7 illustrates a block diagram of an embodiment of the method of identification and improvement of user speech, of the wireless system and apparatus and set for recording, processing and reproduction of sounds in persons with dystrophy in the respiratory system, in accordance with The present invention.
  • Figure 8 illustrates a schematic diagram of the method of operation of the apparatus for the identification and improvement of user speech, in accordance with the present invention.
  • Figure 9 illustrates a block diagram of the processing for the analysis of fluency and speech recognition of the wireless system and apparatus and set it for recording, processing and reproduction of sounds in persons with dystrophy in the respiratory system, in accordance with the present invention.
  • Figure 10 illustrates a schematic diagram of one of the processes implemented for the adjustment of audio and / or reproduction through the implementation of neural networks.
  • the system is comprised of three components defined by a wearable non-invasive device and / or apparatus (1) of the throat vibration type with microphones and wireless communication, a mobile platform (2) and a server / cloud (3).
  • the wearable non-invasive device and / or apparatus (1) of the throat vibration type, with microphones and wireless communication has a sound source module (1.1); a signal acquisition module (1.2); a signal conditioning module (1.3); a logical processing and control module (1.4); a wireless communication module (1.5) and an external power source (1.6) with which said device is connected to a local network (1.7) and to the external server / cloud (3) and interacting with the mobile platform (2).
  • the sound energy source module (1.1) consists of one or more of two multivibrator elements or oscillatory / vibratory transducers (1.1.1) which are placed directly on the patient's neck to create a sound energy source and are actuated by pressure sensor means and / or a button or switch and / or a muscle electrical activity detector (not shown).
  • the multivibrator elements or oscillatory / vibratory transducers (1.1.1) are connected to an electronic power circuit (1.1.2) for speed and intensity adjustment, which produces an adjustment in the tone and power of the sound energy source .
  • the electronic power circuit (1.1.2) is connected directly to the processing module and logical control (1.4).
  • Said signal acquisition module (1.2) consists of a plurality of microphones (1.2.1) that define a network of microphones superimposed on the neck (4) and close to the user's oral cavity for measuring the amplitude modulated wave which are connected directly to the signal conditioning module (1.3) by means of metal cables. It is intended to capture the sound emitted by the sound source with the variations in energy, amplitude and frequency caused by the movement of the pharynx or throat. Said signals reach the signal conditioning module (1.3).
  • Said plurality of microphones (1.2.1) may be subject to a flexible fabric and / or to a rigid support, which allows them to be placed in different positions for an increase in the pickup of sound waves (see figures 3 to 5).
  • Said signal conditioning module (1.3) is formed by an electronic circuit with a high impedance differential input (1.3.1); a preamp (1.3.2), a bandpass filter (1.3.3) with the bandwidth adjusted according to the oscillation frequency of the multivibrator between 80-1000 Hz and / or 1000-6000Hz (high pass filter (1.3. 3a) and low pass filter (1.3.3b)); finally an amplifier (1.3.4) to obtain a signal limited in voltage and frequency for each of the microphones and / or pressure sensors and / or activity sensors electrical muscle and is fed from the external power source (1.6).
  • This module connects directly to the logical control and processing module (1.4) by means of metal tracks on a flexible and / or rigid card.
  • Said processing and logical control module (1.4) allows to obtain information on the conditioned signal, process it and send it. What is divided into four stages:
  • ADC stage (1.4.1) conversion of the signal from the analog to digital filtering stage of the signal (bandpass filter (1.3.3) of the signal conditioning module (1.3) and at the same time the information is stored in the internal and / or external memory (1.5.1) of the wireless communication module (1.5).
  • FIR and MR type digital filters are implemented to eliminate the parasitic frequencies produced by oscillatory / vibratory multivibrators or transducers (1.1.1) , subsequently the information is packaged in blocks such as [a 11, a12. a1n] of n-dimensions to be sent by the wireless communication module (1.5).
  • Connectivity control stage (1.4.4) that allows adjusting the speed, and sending and receiving information of the device to adjust the device, algorithms, digital filters among others.
  • Said wireless communication module (1.5) consists of a circuit not limited to a Bluetooth, wifi, in order to establish connection of the device with the local network (1.7), the mobile platform (2) and with the server / cloud (3 ) to transfer information packets using TX / RX signals (1.5.2).
  • the external power source (1.6) consists of an external power source such as a lithium battery with a voltage range of 1.8-3.7 V which serves to power modules 1.1 to 1.5.
  • the local network (1.7) receives the TX / RX signals (1.7.1), performs a main storage (1.7.2), implements digital filtering types FIR and MR (1.7.3) (Finite Response Filters and Infinite Response Filters ) to eliminate the parasitic frequencies produced by the multi vibrators or oscillatory / vibratory transducers (1.1.1), execute the data and / or voice processing through a loudspeaker (1.7.4) and execute a connectivity with the server (1.7 .5).
  • FIR and MR 1.7.3 (Finite Response Filters and Infinite Response Filters )
  • the server / cloud (3) comprises a connectivity module with the local network (3.1) and executes the speech optimization algorithms (3.2).
  • the device and / or wearable non-invasive device (1) of the throat vibration type, with microphones and wireless communication has a collar-shaped structure and in the frontal area that will be attached to the throat It comprises the signal conditioning module (1.3), the logical control and processing module (1.4), the wireless communication module (1.5) and the external power source (1.6). Near one end there is a cavity (5) adapted to receive oscillatory / vibratory multivibrators or transducers (1.1.1) (see figures 3, 6, 6a and 6b).
  • a plurality of cavities (6) for the placement of plurality of microphones (1.2.1) (see Fig. 3) and / or pressure sensors are included.
  • Figure 5 shows a representation of a user (7) to whom the device and / or non-invasive device (1) of throat vibration type, with microphones and wireless communication, showing the arrangement of multivibrators or transducers is placed oscillatory / vibratory (1.1.1) and the plurality of microphones (1.2.1).
  • said multivibrator elements or oscillatory / vibratory transducers (1.1.1) comprise a housing (8) with an array of components formed by a magnetic system of repulsion and retraction (9) defined by a shaft (10) which at one end comprises a metal disk (11) and near the opposite end comprises a flexible membrane (12); a magnet (13) housed in the housing (8) and a cover (14).
  • the multivibrator elements or oscillatory / vibratory transducers (1.1.1) are subject to a flexible fabric and / or a rigid support and connected to the electronic circuit of power (1.1.2) and to the logical control and processing module (1.4) (see figure 3).
  • the flexible membrane (12), together with the cover (14) and the housing (8) allows the magnetic system of repulsion and retraction (9) to return to its original position and oscillate in a range of 1 Hz to 20kHz Said oscillatory movements, allow to increase the pressure of the adjacent individuals in the cover (14) and generate a wave with sufficient power to be a constant sound source.
  • This constant transport wave when superimposed on the neck (4, see fig. 5), is propagated through the oral cavity where a new wave modulated in amplitude and / or frequency is produced when gesturing, which is subsequently captured by the plurality of microphones (1.2.1).
  • the male voice has a range between 100 and 200 Hz, while the female voice is typically between 150 and 300 Hz.
  • the range Recommended characteristic is 1000 to 6000 Hz, which allows generating a transport wave with the power and frequency to be picked up by the plurality of microphones (1.2.1) and subsequently filtered analogically and / or digitally by a band pass filter (1.3.3, see figure 3).
  • a range of oscillation from 50 to 1000 Hz is contemplated, due to the fact that there are patients with muscular hardening, which makes it difficult to capture the wave modulated in amplitude and / or frequency, by the plurality of microphones (1.2.1). Additionally, you must add a digital filter, which you can contemplate, but limit to a WIENIER filter, since a frequency splice is generated.
  • the multivibrator elements or oscillatory / vibratory transducers (1.1.1) are actuated by means of a logic control of the threshold type. Actuated by exceeding a calibration parameter, manually adjusted by user (7).
  • the measurand that compares to the calibration can come from a pressure sensor, sensors of electrical muscular activity and / or a button.
  • the method of identification and improvement of the user's speech within one of the possible embodiments of the invention when the device and / or non-invasive device (1) is switched on first determines whether there is electrical activity or if the button (b) is being pressed, if the process is not fulfilled, if it is fulfilled then a sound wave (c) is generated that the microphones (d) record; Next, it is determined whether the activity log (e) of not completed, return to Section “c” and in a positive case, the signal processing (f) is then executed, then the signal (g) is filtered and subsequently connected to the local network / server (h) and finally executed Enhanced audio playback on the local network (i).
  • the device and / or non-invasive device (1) when the device and / or non-invasive device (1) is on, it is constantly measuring the electrical muscle activity and / or the pressure sensor and / or waiting for the trigger button (X) in low consumption of energy (X 1); once the threshold is exceeded, the muscular electrical activity (X 2) is identified and the generation of the transport wave is started, the recording of the plurality of microphones (X 3) of the amplitude and frequency modulated wave is initiated by the gesticulation, once a buffer is filled, the complete register (X4) is stored and the complete register is sent (X 5) to the information processing modules (X 6) where the signal is filtered, connectivity is made to the local server and the audio is improved (X 7) immediately the audio reproduction is executed in the local network (X 8) to finally finish the activity recording (X 9).
  • Y various information processing techniques
  • Y1 to normalize the signal
  • Y2 where implement and execute Wiener Filter and / or adaptive filter (Y 3);
  • a time-frequency analysis (Y4) is also performed where they are implemented, by way of example but not limited, FFT, Wavelet Transformed (Y5) for the extraction of main characteristic values (Y6) of each processing [S f 1, S f 2,, S fn]. and it is determined if the entire sample has been processed (Y7) if not, the process is restarted (U ' ) and if finally fulfilled, the audio enhancement is adjusted and the information is reproduced in the plurality of microphones (Y8) or mobile platform speakers (2) of the user's message.
  • the local network communicates with external servers / cloud through calls to services where it stores raw recording, features [S f 1, S f 2, ..., Sfn] and a user feedback when the playback was not correct.
  • These parameters are used in artificial intelligence methodologies as neural networks for the identification of speech patterns and / or similar phonetically words.
  • the information, optimization and adjustment of the voice filtering and reconstruction algorithms are executed on the server.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Hematology (AREA)
  • Emergency Medicine (AREA)
  • Anesthesiology (AREA)
  • Pulmonology (AREA)
  • Cardiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Transplantation (AREA)
  • Vascular Medicine (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

L'invention concerne un système et un dispositif pour l'enregistrement, le traitement et la reproduction de sons chez des personnes présentant une dystrophie du système respiratoire. Ledit dispositif est caractérisé en ce qu'il comprend trois composants communiquant entre eux définis par un dispositif non effractif portable de type à vibration de la gorge qui capte le son émis par la source sonore avec les variations d'énergie, d'amplitude et de fréquence provoquées par le mouvement du pharynx ou de la gorge; conditionne des signaux pour obtenir un signal limité en tension et fréquence ; les convertit d'analogique à numérique, les filtre et les conditionne ; règle la vitesse et l'intensité ce qui se traduit par un réglage de la tonalité et de la puissance de la source d'énergie sonore traitée. Ledit dispositif comprend aussi une source d'énergie externe qui alimente la pluralité de modules ; un module de communication sans fil qui permet la connectivité dudit dispositif à un réseau local et à un serveur externe/infonuagique pour le traitement numérique, le stockage d'information, l'optimisation et l'ajustement des algorithmes de filtrage et la reconstruction de la voix et l'interaction avec une plateforme mobile (cellulaire, tablette et/ou téléphones intelligents), avec au moins un type de connexion sans fil et avec des sonneries ou systèmes de reproduction sonore, dans lesquels est traitée, reconstruite et exécutée la voix dérivée des informations captées par le dispositif et le traitement numérique dans ledit serveur externe/infonuagique.
PCT/MX2018/000079 2018-08-28 2018-08-29 Système et dispositif sans fil et portable pour enregistrement, traitement et reproduction de sons chez des personnes présentant une dystrophie du système respiratoire WO2020046098A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MXMX/A/2018/010369 2018-08-28
MX2018010369 2018-08-28

Publications (1)

Publication Number Publication Date
WO2020046098A1 true WO2020046098A1 (fr) 2020-03-05

Family

ID=69644639

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MX2018/000079 WO2020046098A1 (fr) 2018-08-28 2018-08-29 Système et dispositif sans fil et portable pour enregistrement, traitement et reproduction de sons chez des personnes présentant une dystrophie du système respiratoire

Country Status (1)

Country Link
WO (1) WO2020046098A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112245740A (zh) * 2020-11-04 2021-01-22 湖南万脉医疗科技有限公司 一种基于云平台自检的多功能呼吸机
US11363386B1 (en) * 2020-12-02 2022-06-14 National Applied Research Laboratories System for converting vibration to voice frequency wirelessly

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3072745A (en) * 1959-03-12 1963-01-08 Bell Telephone Labor Inc Unitary artificial larynx
EP1083769A1 (fr) * 1999-02-16 2001-03-14 Yugen Kaisha GM & M Dispositif de conversion de la parole et procede correspondant
JP2005150884A (ja) * 2003-11-12 2005-06-09 Yuji Hosoi 電気人工喉頭

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3072745A (en) * 1959-03-12 1963-01-08 Bell Telephone Labor Inc Unitary artificial larynx
EP1083769A1 (fr) * 1999-02-16 2001-03-14 Yugen Kaisha GM & M Dispositif de conversion de la parole et procede correspondant
JP2005150884A (ja) * 2003-11-12 2005-06-09 Yuji Hosoi 電気人工喉頭

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
"Electrolarynx", 7 August 2018 (2018-08-07), Retrieved from the Internet <URL:https://in.wikipedia.org/w/index.php?tittle=Electrolarynx&oldid=853789784> [retrieved on 20190429] *
"Wiener filter", 26 March 2018 (2018-03-26), Retrieved from the Internet <URL:https://in.wikipedia.org/w/index.php?title=Wiener_filter&oldid=832539875> [retrieved on 20190429] *
A, KHALIL AHMAD: "Wavelet Packets and Their Statistical Applications", 23 June 2018 (2018-06-23), Retrieved from the Internet <URL:https://www.springer.com/the/book/9789811302671#> [retrieved on 20190503] *
G. BALLOU, HANDBOOK FOR SOUND ENGINEERS, 1 April 2015 (2015-04-01), XP055697015, Retrieved from the Internet <URL:https://www.crcpress.com/Handbook-for-SoundEngineers/Ballou/p/book/9780415842938> [retrieved on 20190503] *
T. IFUKUBE: "Sound-Based Assistive Technology: Support to Hearing, Speaking and Seeing", 9 March 2017 (2017-03-09), pages 169 - 197, Retrieved from the Internet <URL:https://link.springer.com/chapter/10.1007/978-3-319-47997-2_6> [retrieved on 20190430] *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112245740A (zh) * 2020-11-04 2021-01-22 湖南万脉医疗科技有限公司 一种基于云平台自检的多功能呼吸机
US11363386B1 (en) * 2020-12-02 2022-06-14 National Applied Research Laboratories System for converting vibration to voice frequency wirelessly

Similar Documents

Publication Publication Date Title
US10904664B2 (en) Device for generating chest-chamber acoustic resonance and delivering the resultant audio and haptic to headphones
US9380374B2 (en) Hearing assistance systems configured to detect and provide protection to the user from harmful conditions
US5326349A (en) Artificial larynx
US9210517B2 (en) Hearing assistance device with brain computer interface
JP4702795B2 (ja) 体内伝導音マイクロフォン、信号処理装置、コミュニケーションインタフェースシステム、採音方法
US20150133716A1 (en) Hearing devices based on the plasticity of the brain
CN101123915B (zh) 声监控器
CN106464995A (zh) 用于体育活动的独立多功能耳机
JP2009539332A (ja) 音声信号処理のための方法および装置
CA2795555A1 (fr) Microphone a conduction tissulaire intra-buccal
WO2020046098A1 (fr) Système et dispositif sans fil et portable pour enregistrement, traitement et reproduction de sons chez des personnes présentant une dystrophie du système respiratoire
US20240089679A1 (en) Musical perception of a recipient of an auditory device
WO2021214065A1 (fr) Greffage vocal à l&#39;aide d&#39;un apprentissage automatique
CN106344064A (zh) 一种音频信号采集装置及采集方法
JP4130443B2 (ja) マイクロフォン、信号処理装置、コミュニケーションインタフェースシステム、音声話者認証システム、ｎａｍ音対応玩具装置
CN105704603A (zh) 蓝牙耳机
US20160078779A1 (en) Wireless stethobroadcasting instrument for medical training
KR20170100932A (ko) 이마와 콧등을 이용한 무호흡방지장치
US20220417678A1 (en) Methods and Systems for Auditory Nerve Signal Conversion
US20210153461A1 (en) Noise attenuation earphone device for animals
US20230209279A1 (en) Methods and Systems for Auditory Nerve Signal Conversion
KR100681484B1 (ko) 인공 후두장치
CN113317909B (zh) 一种多维度智能人工喉
JP2005354295A (ja) マイクロフォン、コミュニケーションシステム、コミュニケーション方法
JP2021111934A (ja) 音響機器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18931657

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18931657

Country of ref document: EP

Kind code of ref document: A1