35 results about "Vocal fold vibration" patented technology

It is possible to improve a defect of an analysis object itself of a mobile telephone and speech recognition which is an air propagating normal speech taken from outside by a microphone and realize a new mobile terminal communication based on the human cultural habit in the personal mobile information terminal without requiring training. A stethoscope type microphone is mounted on a human skin surface so as to take a meat-propagating vibration sound of un-hearable murmur articulated by a speech act (mouth movement) without using vocal cord regular vibration. The meat-propagating vibration sound of the amplified non-hearable murmur is like a whisper and the whisper itself can be heard and understood by a human. Accordingly, it can be used for communication via a mobile telephone. Moreover, by making the meat-propagating vibration sound of the un-hearable murmur an object of analysis / parameterization, it is possible to realize a kind of soundless recognition as a new input method of a personal mobile information terminal.

A system for imaging high speed moving objects, for example, using a scanning beam and beam delivery optics with fast signal processing. It can allow for vocal fold imaging at up to or exceeding approximately 1000 frames per second with grayscale resolution as high as about 100 micrometers or higher and up to about a 12.4 mm square or larger viewing area. The invention can provide imaging of vocal fold vibration that correlates completely with a synchronously-acquired acoustic voice signal. This can enable physicians, voice therapists and research scientists to understand the consequences of abnormal laryngeal dynamics, rather than being limited to simply observing the dynamics. Further, the application of laser technology will allow for accurate measurements of dimension. This can objectify examination findings and treatment outcomes measurement, helping to overcome the serious limitations of current perceptual-based judgments.

A method and system for the assessment and diagnosis of voice in normal and diseased states can include determining at least one quantitative measure of vocal fold vibration using a laryngeal image recording of a subject's vocal fold obtained from an endoscopic device or an auditory recording of a subject during a phonatory task, and can include subsequent analysis of a waveform selected from waveform types comprising a) an acoustic recording, and b) a glottal waveform that is extracted from the laryngeal image recording. The method and system can generate a comprehensive, at-a-glance, physician friendly visual pattern and characteristics of vocal fold vibrations and correlate with specific voice conditions for diagnosis and assessment of voice and therapies and treatments of voice disorder.

The invention relates to a detecting system and method for the mechanical properties of vocal fold vibration. The detecting system comprises a high-speed photography laryngoscope module, a high frame rate ultrasound module, a data acquisition module, a synchronous acquisition control module, an image display module, a data storage module, an imaging data processing module and a mechanics parameter extraction module; a high-speed photography laryngoscope and high frame rate ultrasound are respectively connected with the same computer. The detecting method comprises the following steps: 1) setting corresponding acquisition duration and storage path; 2) ensuring a high frame rate ultrasound probe to cling to the side of throat and inserting the high-speed photography laryngoscope from an oral cavity; 3) regulating related parameters of ultrasound and position and focus of the high-speed photography laryngoscope; 4) ensuring persons to be detected to vocalize and synchronously acquiring and storing data; 5) extracting glottis area and somatic layer shift; 6) extracting the mechanics parameter of vocal fold vibration. The invention provides a quantitative extracting method of the mechanics parameter of vocal fold vibration, thus obtaining the mechanics parameter of vibration of a vocal fold cover layer and the somatic layer with different mechanical properties.

The invention discloses a device for simulating human vocal cord vibration. The device comprises a vocal cord model channel, a vocal cord model, a frequency conversion device, a vacuum pump, an air measurement system, a vibration measurement system, a particle picture speed measurement system, a data acquisition card and a computer, wherein the frequency conversion device is connected with the vacuum pump, and the vacuum pump is arranged at one end of the vocal cord model channel; the air measurement system and the vibration measurement system are arranged on the vocal cord model channel, and output ends of the air measurement system and the vibration measurement system are both connected with the data acquisition card; and the data acquisition card is connected with the computer. A method for simulating the human vocal-cord vibration by using a physical model is designed by the invention; and an emulational vocal cord is simulated by adopting a spring-mass block-damping model theory, and a particle picture speed measurement device is induced, which provides a support for researching and establishing a relation between the vocal cord and a sound production parameter. The method can be used for providing a support for medical researches of vocal cord vibration characteristics and the like under different sound production conditions and different pathological change conditions.

The invention discloses a vocal-cord vibration nondestructive measurement method by utilizing a natural vocal track ultraphonic waveguide effect. The method comprises the following steps of: stimulating an ultrasonic wave through an air ultrasonic transducer, and guiding the ultrasonic wave into an oral cavity and a vocal track; transmitting the ultrasonic wave in a natural acoustic waveguide formed by a vocal track of a human body to arrive a vibrated vocal track; through reflection of a surface of the vocal track, transmitting the ultrasonic wave back to the oral cavity through the vocal track, and detecting a reflection echo through the air ultrasonic transducer; after digitalizing a reflection signal, computing frequency deviation of the reflection signal relative to a transmitting signal; obtaining relative movement speed of a refection surface of the ultrasonic wave (i.e. the surface of the vocal track) through a doppler frequency shift formula; and integrating a speed value so as to obtain a movement displacement signal of the reflection surface of the ultrasonic wave. According to the vocal-cord vibration nondestructive measurement method provided by the invention, the ultrasonic transducer has no need to be stretched into the deep part of the vocal track, an examined patient has no need to maintain a particular body posture to straighten the vocal track, and higher safety and usability are realized.

The invention relates to a method for separating sound of single channels on the basis of human sound models. The method includes steps of building the human sound models by the aid of source filters; providing input signals; constructing human sound power of the input signals by the aid of vocal cord vibration power models and filter models of vocal tracts and oral cavities; constructing background sound power of the input signals; reconstructing signal power spectra of the input signals according to the constructed human sound power and the constructed background sound power; solving human sound power and background sound power in the reconstructed signal power spectra and separating human sound signals and background sound signals from the input signals according to the solved human sound signals and the solved background sound signals. The built human sound models comprise the vocal cord vibration power models and the filter models of the vocal tracts and the oral cavities. The method for separating the sound of the single channels has the advantages that human sound can be separated from background sound by the aid of the method under extremely noisy conditions, and the method can be used in the fields of speech enhancement, human sound extraction and the like and is high in practicality.

The invention discloses a singing tone quality detection device with closed characteristics. The singing tone quality detection device comprises a laryngoscope, a light source, a computer and a high-speed glottis video camera system. Through the laryngoscope and the high-speed glottis video camera system, images of vocal cords are acquired. The image information is transmitted to the computer. Thecomputer performs data analysis on the image information and the vibration rule by utilizing vocal cord vibration processing system software of a two-mass block-finite element model. Vocal cord vibration waveforms and vibration parameters in the images are extracted. The operation state of the vocal cord when the vocal cord makes different sounds and the vibration regularity when the vocal cord makes sounds can be visually understood. The defects existing in singing practice can be found through image automatic analysis of vocal cord vibration processing system software of a two-mass-block-finite-element model and the nonlinear analysis function of continuous waveforms, improvement is conducted, and the vocal cord training effect is improved. The method has the characteristics of real-time performance and effectiveness of singing tone quality practice detection, and the working efficiency is improved.

The invention relates to a vibration feedback system and device for speech rehabilitation. The vibration feedback system and device comprise a video acquisition module, a video processing module, a speech acquisition module, a speech processing module, a synchronous processing module, a data transmission module, a data display module, a vibration acquisition module, a signal processing module anda vibration feedback module. The invention provides an audio and video recognition system; meanwhile, the video acquisition module and the vibration feedback module are added to assist deaf students in a visual three-dimensional human face speech production model and vocal cord vibration simulation during hearing-speech rehabilitation training; the vibration feedback module can feed back the vocalcord vibrating condition in the speech production process of deaf children and gives feedback; the vibration feedback system is a rehabilitation system fusing mentor simulation of speech production process by three-dimensional virtual speech, vocal cord vibrating simulation and vibration information feedback and assisting speech training of the deaf students.

A voice analyzing apparatus comprises: a first analyzer that analyzes a voice into harmonic components and inharmonic components: a second analyzer that analyzes a magnitude spectrum envelope of the harmonic components into a magnitude spectrum envelope of a vocal cord vibration waveform, resonances and a spectrum envelope of a difference of the magnitude spectrum envelope of the harmonic components from a sum of the magnitude spectrum envelope of the vocal cord vibration waveform and the resonances; and a memory that stores the inharmonic components, the magnitude spectrum envelope of the vocal cord vibration waveform, resonances and the spectrum envelope of the difference.

The invention discloses a voice synthesis method based on voice radar and videos. The method comprises the following steps: acquiring vocal cord vibration frequency as basic voice frequency from a radar echo signal; fitting movement characteristics extracted from lip video information of a speaker in talking with a resonance peak extracted from microphone synchronous acquired voice signals, and acquiring an experience equation of a mapping relationship of the lip movement characteristics and the resonance peak; by taking a lip video of a tester in talking as input, acquiring a time-varying resonance peak; and finally, carrying out voice synthesis on obtained basic frequency and the time-varying resonance peak. By adopting the method disclosed by the invention, voice radar can be combined with image information without contacting a speaker, and voice synthesis can be achieved.

The invention discloses an ear canal microphone, and relates to the voice frequency communication technology. A sound pickup (4) is arranged at an eardrum end (203) of an ear canal cylinder (202), the sound pickup (4) collects eardrum vibration or / and ear canal vibration in an ear canal to recover a voice signal, the eardrum vibration or / and the ear canal vibration is caused by vibration of the vocal cord of a speaker, and is caused through bone conduction, the sound pickup (4) does not collect a sound wave of noise in the external environment of the ear canal of a user, and the obtained voice signal is pure. The ear canal microphone can especially meet the requirement of the voice intelligent control technology for the degree of pureness of a key word, is a front end bottleneck device necessary for promoting practicability of the voice intelligent control technology, and also improves voice communication in the noisy environment.

The invention discloses a voice emotion recognition method based on glottal wave signal feature extraction. According to the method, a spectrogram and TEO are mainly adopted as input of CRNN, a low-level descriptor and a high-level statistical function are combined, emotional speech features are extracted, subjected to dimensionality reduction and subjected to an identification algorithm, and finally output is conducted through an HSF channel. The glottal wave signal feature extraction mainly realizes signal acquisition in a complex cepstrum phase decomposition form, a PCA method is adopted toreduce the dimension of a feature vector, and a BP neural network algorithm is adopted to identify and output the feature vector. According to the method, vocal cord vibration characteristics can bebetter reflected, glottis open-phase and closed-phase information is clear, sound source harmonic components and sound channel interference are effectively reduced, and the recognition accuracy is high.

The invention belongs to the technical field of voice recognition, solves the technical problem of low accuracy of judging baby cry through voice recognition, and provides a method, a device and equipment for identifying baby cry category through multi-feature fusion. The method comprises the following steps: acquiring an audio feature when a baby cries, an action feature value of a posture action and a vibration spectrum of vocal cord vibration; converting the actionfeature value into a standard feature value in a database; based on the standard feature value, performing feature fusion on the audio feature and the vibration spectrum; inputting the fused features into a preset neural network, and obtaining the cry category of the baby according to a coding feature vector output by the neural network, wherein the standard feature value is a probability value of each cry category represented by the corresponding posture action. The invention further comprises a device for executing the method and equipment According to the method, the requirements of the baby are enhanced by utilizing the posture features, so that misjudgment can be reduced, and the cry detection accuracy is improved.

The invention relates to a vocal cord vibration phonation efficiency measuring system. The phonation efficiency can quickly reflect the differences between the normal condition and pathological condition. The invention comprises the sensor module, signal pre-processing module, AD converter, central control module, keyboard input and the LED display module, single chip module and PC interaction module, software processing module. The sensor module comprises the sound pressure, air flow sensor and sound level meter which is the microphone; the outputs of the sound pressure sensor, gas flow sensor and microphone are connected to the input of the signal pre-processing module. The output of the signal pre-processing module is connected to the input of the AD converter. The output of the AD converter is connected to the signal input of the central control module. The keyboard input and the LED display are also connected to the signal input of the central control module; the signal output of the central control module is connected to the single chip and the PC interaction module. The output of the single chip and the PC interaction module are connected to the software processing module.

The invention discloses a silent speech recognition method and system. The method comprises the following steps: acquiring facial electromyographic signal data and vocal cord vibration signal data during speaking; respectively preprocessing two types of acquired data, extracting and fusing features, and sequentially performing training and identifying by using deep learning; and sending the identified command result to the receiving equipment or the controlled equipment. The system comprises a data acquisition module, a signal processing module and a communication interaction module. Comparedwith a silent speech recognition method based on a single signal, the silent speech recognition method integrates two characteristic signals used in a silent speech recognition technology, including afacial electromyographic signal and a vocal cord vibration signal, so that higher recognition accuracy can be obtained.

The invention discloses a non-contact time varying vocal cord vibration detection signal processing method. The method comprises the following processing steps: sending, by a non-contact time varyingvocal cord vibration detection system, orthogonal two-path signals, and performing complex demodulation on the orthogonal signals to obtain orthogonal demodulated signals; performing band-pass filtering, endpoint detection and segmentation on the orthogonal demodulated signals, decomposing fundamental frequency and higher harmonics by using a variational modal decomposition algorithm, then performing mode selection on the voice fundamental frequency obtained by manually calibrating microphone voice signals to obtain a vocal cord vibration fundamental frequency signal waveform, and performingtime frequency analysis and smoothing on the vocal cord vibration signal waveform to obtain a time varying vocal cord vibration frequency. The method is simple and easy to implement.

The invention discloses a voice control system and method of a hydraulic support based on vocal cord vibration measurement. The method comprises the steps that the vocal cord vibration of an operatoris converted into a corresponding electrical signal through a vibration measurement unit; the electrical signal is amplified by a signal amplification unit, then converted by a vibration signal A / D conversion unit and then transmitted to a signal processing unit for analysis and processing to obtain a voice control command corresponding to the vocal cord vibration signal; and then the voice control command is compared and matched with a standard voice control command to indentify the vocal cord of the operator, the control signal corresponding to the vocal cord is sent to a hydraulic support controller wireless transceiver unit through a wireless signal transceiver unit, and at the same time, the hydraulic support controller wireless transceiver unit feeds back the status parameters of thehydraulic support. The voice control system of the hydraulic support based on the vocal cord vibration measurement is simple to operate, the operator only needs to give the voice control command, andthe hydraulic support can make corresponding actions; and accurate recognition of the voice control command in a noisy environment can be realized, and the voice control method can be used as an auxiliary control method to ensure the normal operation of the hydraulic support.

The invention discloses a mathematical formula memorizing device convenient for communication, and aims at solving the problem of low formula memorizing efficiency in the prior art. The mathematical formula memorizing device comprises lighting lamps, observation windows, universal tubes, connecting blocks, head hoods, elastic cords, protective blocks, slide blocks, spiral springs, guide rods, stopblocks, a connecting ring, connecting rods, locating rods, clamp blocks, balls and paper cones. The invention relates to the field of mathematics teaching. The vocal cord vibration frequency and amplitude of the teacher can be observed through cooperation of the arranged paper cones and the balls so that learning of the pronunciation of the mathematical symbol can be facilitated and memorizing ofthe mathematical formula can be more easily performed. Two protective blocks are arranged so that the student is enabled to learn and memorize the mathematical formula along with the shape of the mouth of the teacher, the learning interest of the student can be increased, the formula memorizing effect can also be enhanced, the design is reasonable, operation is convenient and the mathematical formula memorizing device is worthy of popularization.

The invention provides a bionic device for simulating vocal cord vibration by utilizing double-lamination transducers. A simulation box is used for simulating a vocal track cavity. Left and right muscle simulation layers in the simulation box and first and second double-lamination transducers between the left and right muscle simulation layers vibrate are utilized to simulate the vocal cord vibration and drive muscles to act to hinder the stretching and the vibration of a vocal cord to simulate the sound production of human vocal cords in different states, the lengths of the piezoelectric ceramic transducers are regulated to simulate the vibration of different human vocal cords and the vibration of vocal cords with pathological changes, and the amplitude of alternating current voltage is regulated to simulate the vibration of the vocal cords for producing high-pitched sounds or low-pitched sounds, so that the vibration of the vocal cords under different vibration frequency and different vibration amplitude is simulated, and vocal cord structures are simulated in a multi-level way. Moreover, the bionic device is simple in structure and convenient to operate.

The invention relates to a method for controlling a microphone switch by a three-axis acceleration sensor, electronic equipment and a computer readable storage medium. The method is used for reducingthe power consumption of an earphone, and comprises the following steps: step A, starting the three-axis acceleration sensor in the earphone to carry out X, Y and Z three-axis data acquisition on vocal cord vibration caused by skull attached muscles when a user speaks, and controlling the Z axis of the three-axis acceleration sensor to be perpendicular to the direction of ears of the user and parallel to the horizontal direction in the acquisition process; step B, cyclically detecting an energy accumulation value of Z-axis data in a period according to a set detection period, and triggering tostart the microphone to pick up sound when the energy accumulation value of the Z axis exceeds a set bone vibration switch threshold value; and step C, after the microphone is started, if the energyaccumulation value of the Z axis is not detected to exceed the bone vibration switch threshold after the set duration is continuously exceeded, turning off the microphone.

The invention relates to a method for separating sound of single channels on the basis of human sound models. The method includes steps of building the human sound models by the aid of source filters; providing input signals; constructing human sound power of the input signals by the aid of vocal cord vibration power models and filter models of vocal tracts and oral cavities; constructing background sound power of the input signals; reconstructing signal power spectra of the input signals according to the constructed human sound power and the constructed background sound power; solving human sound power and background sound power in the reconstructed signal power spectra and separating human sound signals and background sound signals from the input signals according to the solved human sound signals and the solved background sound signals. The built human sound models comprise the vocal cord vibration power models and the filter models of the vocal tracts and the oral cavities. The method for separating the sound of the single channels has the advantages that human sound can be separated from background sound by the aid of the method under extremely noisy conditions, and the method can be used in the fields of speech enhancement, human sound extraction and the like and is high in practicality.

The invention discloses a voice recognition method based on the glottis wave information. The method comprises three steps of source signal preprocessing, feature extraction, and classification and recognition, wherein the source signal preprocessing extracts a glottis wave signal of an original voice signal as a source signal for feature extraction; the feature extraction adopts a dynamic image expert group standard MPEG-7 to extract an audio high-order statistic feature, and combines the audio high-order statistic feature with an openSMILE feature and a classic glottis feature to serve as a feature set for glottis wave signal identification; classification and recognition are based on a random forest classifier, and prediction and classification of speech recognition are carried out by adopting a ten-time cross validation method. According to the method, glottis waves are used as source signals, the effects of glottis excitation and vocal cord vibration mechanisms in speech recognition are fully represented, and a dynamic image expert group standard MPEG-7 is proposed to extract audio high-order statistical characteristics and combine the audio high-order statistical characteristics with openSMILE characteristics and classic glottis characteristics to serve as a recognition characteristic set; a problem of inter-frame repetition and over-fitting is solved, and meanwhile, the method does not depend on a fundamental tone frequency estimation result.

The invention relates to a tracheotomy catheter capable of meeting the speaking requirement. According to the technical scheme, the tracheotomy catheter capable of meeting the speaking requirement comprises an inner catheter used for forming a breathing support air channel and an external tracheotomy tube capable of being arranged on the inner catheter in a sleeving mode. A vocal cord vibration airflow branch can be formed through cooperation of the external tracheotomy tube and the inner catheter, and the vocal cord vibration airflow branch and the breathing support air channel formed by the inner catheter are isolated from each other and independent of each other so that the breathing support air channel can be used for carrying out needed breathing support and / or the vocal cord vibration airflow branch can be used for providing airflow needed by vocal cord vibration. After tracheotomy intubation, the speaking requirement can be met, language communication between a tracheotomy patient and medical staff is effectively achieved, and the tracheotomy catheter is convenient to use, safe and reliable.

A method for obtaining vocal cord medical detection image information comprises the steps that firstly, mechanical signals generated when vocal cords vibrate are obtained and converted into vocal cord vibration electric signals, and the vocal cord vibration electric signals are square wave signals; and 2, selecting a rising edge of the vocal cord vibration electric signal as a trigger signal according to a set mode to obtain a vocal cord medical detection image. The invention also provides a system for acquiring vocal cord medical detection image information, comprising: a vibration sensor, the vocal cord vibration electric signal generated by the vibration sensor being a square wave signal; an image sensor is arranged in the laryngoscope lens; and the endoscope host is provided with a processor. The device has the characteristic of self-adaption to the vocal cord vibration frequency, a video image when the vocal cord is located at a certain fixed position can be observed, stable image display is achieved, and medical staff can conveniently check vocal cord diseases.

The invention discloses a device for simulating human vocal cord vibration. The device comprises a vocal cord model channel, a vocal cord model, a frequency conversion device, a vacuum pump, an air measurement system, a vibration measurement system, a particle picture speed measurement system, a data acquisition card and a computer, wherein the frequency conversion device is connected with the vacuum pump, and the vacuum pump is arranged at one end of the vocal cord model channel; the air measurement system and the vibration measurement system are arranged on the vocal cord model channel, and output ends of the air measurement system and the vibration measurement system are both connected with the data acquisition card; and the data acquisition card is connected with the computer. A method for simulating the human vocal-cord vibration by using a physical model is designed by the invention; and an emulational vocal cord is simulated by adopting a spring-mass block-damping model theory, and a particle picture speed measurement device is induced, which provides a support for researching and establishing a relation between the vocal cord and a sound production parameter. The method can be used for providing a support for medical researches of vocal cord vibration characteristics and the like under different sound production conditions and different pathological change conditions.

The invention relates to a detecting system and method for the mechanical properties of vocal fold vibration. The detecting system comprises a high-speed photography laryngoscope module, a high frame rate ultrasound module, a data acquisition module, a synchronous acquisition control module, an image display module, a data storage module, an imaging data processing module and a mechanics parameter extraction module; a high-speed photography laryngoscope and high frame rate ultrasound are respectively connected with the same computer. The detecting method comprises the following steps: 1) setting corresponding acquisition duration and storage path; 2) ensuring a high frame rate ultrasound probe to cling to the side of throat and inserting the high-speed photography laryngoscope from an oral cavity; 3) regulating related parameters of ultrasound and position and focus of the high-speed photography laryngoscope; 4) ensuring persons to be detected to vocalize and synchronously acquiring and storing data; 5) extracting glottis area and somatic layer shift; 6) extracting the mechanics parameter of vocal fold vibration. The invention provides a quantitative extracting method of the mechanics parameter of vocal fold vibration, thus obtaining the mechanics parameter of vibration of a vocal fold cover layer and the somatic layer with different mechanical properties.

The invention provides a language training auxiliary system and method for hearing-impaired children. The system includes: a video processing module for calling a computer camera; a server module for storing recorded teaching course videos; a wireless communication module for receiving data from the server module The information processing module ensures that the wireless communication module transmits the data to the output module in time after receiving the data; the output module controls the operation degree of the breath simulation module and the operation degree of the vocal cord vibration simulation module by outputting PWM waves at two GPIO ports; The breath simulation module is controlled by the information processing module to rotate; the vocal cord vibration simulation module is controlled by the information processing module to generate vibration; the voice accuracy feedback module is used to output the audio of hearing-impaired children to the voice recognition interface; the data recording module, For storage and processing of all course data, etc. The invention provides guidance on pronunciation skills, and provides accuracy feedback for a single pronunciation exercise.

The invention discloses a breathing assembly supporting a voice function, a ventilation method thereof and a breathing machine, and the breathing assembly comprises: a monitoring module which is usedfor monitoring the mouth end pressure and the expiratory pressure of a patient; an air suction module which is used for providing air for the patient during air suction; an expiration module which isused for exhausting gas generated by expiration of the patient and further used for controlling the pressure of the expiration branch to be larger than the pressure of the mouth end according to the pressure, monitored by the monitoring module, of the mouth end, wherein meanwhile the pressure of the expiration channel is increased due to lung contraction in the expiration process of the patient, so that gas in the expiration channel of the patient does not pass through the expiration branch, but flow to the mouth, and the vocal cord of the patient vibrates and makes a sound. Compared with a voice valve in the prior art, the breathing assembly does not need to be dismantled, element abrasion can be avoided, and therefore cost is reduced, and meanwhile due to the fact that dismantling is notneeded, clinical operation is easy, and the sound production requirement of a patient can be rapidly met.