9 results about "Vocal fold vibration" patented technology

The application discloses a sound source positioning and identification method and device based on multi-modal fusion and a storage medium, relates to the technical field of sound source positioning, and discloses a sound source positioning and identification method based on multi-modal fusion, which comprises the following steps: detecting a biological target with lip movement characteristics and / or vocal cord vibration characteristics in a scene through a millimeter wave radar, and acquiring the spatial coordinates of the biological target; acquiring the sound source direction angle of a sound source through a microphone array, and generating a corresponding sound source direction vector based on the sound source direction angle; judging whether the biological target is an effective sound production target based on the spatial relationship between the spatial coordinates and the sound source direction vector; and if the biological target is the effective sound production target, determining the identity information of the effective sound production target. The application effectively fuses multi-modal data such as radars and audio, significantly improves the accuracy of sound source positioning and identification, and realizes the technical effects of stable and reliable speaker positioning and identity recognition in a complex environment.

The invention discloses a nasal sound recognition method based on acoustic feature decoupling, which is characterized in that a double-flow decoupling deep neural network is constructed, a mutual information minimization adversarial training strategy is introduced, and sound source features (vocal cord vibration) and sound channel features (oral cavity and nasal cavity adjustment) are forcibly separated from a single audio signal. On the basis, the high-resolution characteristic of CQT is used for accurately extracting acoustic characteristics related to the nasal sound, physiological offset correction is carried out in combination with personal acoustic fingerprints, and finally accurate quantification and recognition of different nasal sound states (normal, defect and skill) are achieved, so that an objective and visual feedback basis with artistic style adaptability is provided for vocal music teaching.

The invention relates to the technical field of medical care and rehabilitation medicine, and discloses a method for establishing reverse airflow to assist sound production through a subglottic suction tube, and the method comprises the following steps: executing airway cleaning, keeping a tracheotomy cannula air bag full, and blocking a tracheal gap by using the air bag; constructing a reverse air supply passage for connecting an external air source and the subglottic suction tube; gas supply equipment is started, and the gas flow is adjusted through a progressive strategy; on-off of a gas path is controlled according to sound production requirements, so that gas is ejected from the subglottic suction tube and is limited by blocking of the air bag to form upward reverse airflow to impact the vocal cord. The air bag is used as a physical barrier to reconstruct subglottic positive pressure, vocal cord vibration is effectively driven to recover the speech function of a patient on the premise that a tracheotomy ventilation mode is not changed and the risk of aspiration by mistake is not increased, the problem that the tracheotomy patient cannot make a sound for a long time is solved, and meanwhile recovery of physiological reflex of the upper respiratory tract is promoted through fluid stimulation.

The application relates to the technical field of speech recognition, in particular to a speech-based emotion recognition method, which comprises the following steps: according to an input speech signal, frame division and windowing are carried out. The application can obtain more profound insights into emotional expression by decomposing the input speech signal into two physical sources of glottal excitation and vocal tract response for independent modeling and analysis, obtaining a vocal tract transfer function set via linear predictive coding operation, and applying inverse filtering to the original speech signal to reconstruct an approximate glottal pulse sequence, effectively stripping the influence of vocal tract resonance on the signal, so that perturbation parameters, open quotient and closed quotient and the like representing vocal cord vibration patterns can be directly calculated, at the same time, the vocal tract transfer function set is used to identify and track the dynamic trajectory of the formant, and the phase difference cosine mean between adjacent frames is combined to quantify the sound production stability, and subtle dynamic adjustment and control stability of sound production organs such as the oral cavity and tongue position caused by emotional changes are captured.

The invention discloses an ear-nose-throat disease early screening method. The method comprises the following steps: a voice acquisition step: acquiring a standardized voice sample of a user through an audio acquisition device; a feature extraction step: extracting multi-level acoustic features including vocal cord vibration features, resonance features, pronunciation stability features and depth representation features from the voice sample; and a baseline establishment step. According to the ear-nose-throat disease early-stage screening method and the ear-nose-throat disease early-stage screening system provided by the embodiment of the invention, the influence of individual voice difference on the screening result is effectively overcome by establishing the individual dynamic voiceprint base line; multi-level acoustic feature analysis is adopted, so that the accuracy of disease recognition is improved; continuous monitoring and dynamic risk assessment are realized, and possibility is provided for early lesion discovery; on the premise of protecting user privacy, model optimization is realized through federal learning; an objective and quantitative auxiliary diagnosis basis is provided for clinicians, and the diagnosis and treatment efficiency is improved.

The invention discloses a sound source localization identification method and device based on multi-modal fusion, and a storage medium, relates to the technical field of sound source localization, and discloses a sound source localization identification method based on multi-modal fusion, and the method comprises the steps: detecting a biological target with a lip movement feature and / or a vocal cord vibration feature in a scene through a millimeter wave radar; obtaining the space coordinates of the biological target; obtaining a sound source direction angle of a sound source through a microphone array, and generating a corresponding sound source direction vector based on the sound source direction angle; judging whether the biological target is an effective sounding target or not based on the spatial relationship between the spatial coordinates and the sound source direction vector; and if the biological target is the effective sounding target, determining identity information of the effective sounding target. According to the method, radar, audio and other multi-mode data are effectively fused, the accuracy of sound source positioning and recognition is remarkably improved, and the technical effect of stable and reliable speaker positioning and identity recognition in a complex environment is achieved.

The present invention relates to a high-quality voice signal processing device and method through ambient noise removal based on multi-sensor signal fusion, which enables voice signal processing robust to external noise environments through multi-sensor signal fusion using an accelerometer sensor (ACC) and a voice microphone sensor (MIC). The device comprises: a voice microphone sensor (MIC) that senses and outputs a voice signal of a speaker; an accelerometer sensor (ACC) that detects vocal cord vibration of a speaker and outputs a signal; a noise reduction processing MCU that extracts a vocalization segment based on vocal cord vibration using the output signal of the accelerometer sensor (ACC), synthesizes the low-frequency component of the accelerometer sensor (ACC) and the low-frequency component of the voice microphone sensor (MIC) by varying the synthesis ratio based on the noise level extracted from the output signal of the voice microphone sensor (MIC) using the vocalization segment information, and restores and outputs a voice signal by adding the synthesized low-frequency component and the high-frequency component of the voice microphone sensor (MIC); and a wireless communication module that outputs the restored voice signal externally.

The semantic recognition method and related apparatus provided in this application relate to the field of terminal technology. The method includes: acquiring data such as the vibration frequency of a user's vocal cords based on the radar of an electronic device, and parsing the radar-acquired data to obtain the semantics the user wants to express. Using radar to detect vocal cord vibration offers good privacy and transmission capabilities. This allows the electronic device to not rely entirely on processing voice signals or lip movements, enabling more accurate semantic recognition even in noisy, dimly lit, or obstructed environments, improving call quality and thus enhancing the user experience.

The application provides a vehicle-mounted intelligent sound field regulation method based on brain waves and surface acoustic waves, comprising: acquiring an acoustic signal in the vehicle and a brain electrical signal of a driver, wherein the acoustic signal is collected by a surface acoustic wave sensor, and the brain electrical signal is acquired by a brain electrical collection device; processing the acoustic signal, extracting mechanical vibration features related to vocal cord vibration, and distinguishing between a vocal signal and a non-vocal signal based on the mechanical vibration features; processing the brain electrical signal, extracting brain electrical features representing the attention state and / or physiological state of the driver; performing multi-modal fusion analysis on the acoustic feature information corresponding to the vocal signal and the brain electrical features, generating a sound field regulation strategy and / or a safety response strategy corresponding to the state of the driver; adjusting the vehicle-mounted audio output according to the sound field regulation strategy to enhance the vocal signal and / or suppress the non-vocal signal; and / or triggering a corresponding safety response operation according to the safety response strategy.