Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

6 results about "Phonation" patented technology

The term phonation has slightly different meanings depending on the subfield of phonetics. Among some phoneticians, phonation is the process by which the vocal folds produce certain sounds through quasi-periodic vibration. This is the definition used among those who study laryngeal anatomy and physiology and speech production in general. Phoneticians in other subfields, such as linguistic phonetics, call this process voicing, and use the term phonation to refer to any oscillatory state of any part of the larynx that modifies the airstream, of which voicing is just one example. Voiceless and supra-glottal phonations are included under this definition.

A method for detecting phonation of EEG signals based on convolutional temporal networks

The present invention discloses a method for detecting the utterance of an electroencephalogram signal based on a convolutional time series network, comprising: performing time-frequency analysis on the original electroencephalogram data as a neural feature; performing envelope analysis on the audio data using the Hilbert transform, annotating the audio data by threshold segmentation, obtaining speech features, and aligning the speech features and the neural features; constructing a convolutional time series network for utterance detection, using the aligned neural features as input data, and constructing a data set with the aligned speech features as true value labels, and training the convolutional time series network for utterance detection; inputting the electroencephalogram signal to be detected into the trained convolutional time series utterance detector after time-frequency analysis, predicting the pronunciation state, and performing utterance detection of the electroencephalogram signal. The present invention achieves performance superior to that of the currently commonly used utterance detectors, and at the same time, the present invention explains the detection performance of the detector, effectively improving the unexplainable problem of the existing utterance detection method based on the neural network.
Owner:ZHEJIANG UNIV

Vocal assessment

A user’s speech patterns are analysed in order to determine mental characteristics (eg. a psychological or psychiatric disorder or mental health condition such as depression, schizophrenia, bipolar disorder or psychosis risk) via different measures of coherence relating to the semantic arrangement of words, different types of connectivity graphs (eg. semantic, contextual or grammatical), and syntactic assessment of words contained within the speech sample (eg. “grammatically sophisticated”). A node 301 represents a word 303, and an edge 302 represents use of two together. Acoustic features (eg. spectral, temporal, phonation or volume parameters) may also be analysed, and the output used to select a treatment.
Owner:PSYRIN LTD

An electronic artificial larynx using control based on facial electromyographic signals

InactiveCN115429487BTracheaeSensorsNoise generationArtificial Laryngeal Speech
The present invention proposes a method and system for controlling the start and stop of vibration of an electronic artificial larynx by using facial electromyographic signals. The sounding of the electronic larynx is controlled by the electromyographic signals generated when the user opens and closes his mouth. The electromyographic acquisition system converts the specially processed facial electromyographic signals into switch signals, which can drive the micro-electric conversion system to generate vibrations. When the lips do not make a sound, the electric power conversion module is controlled to stop working. When the lips make a sound, the electric power conversion module is driven to vibrate to generate the electronic artificial larynx voice after the noise between sounds is eliminated. That is, the electric power conversion module only generates the electronic artificial larynx voice when the user's lips make a sound. When the user's lips do not make a sound and between one sound and the next sound, the electric power conversion module stops working, thereby avoiding the generation of noise. This method can solve the problem of noise interference in the vocalization gap during the vocalization process of the electronic artificial larynx and improve the application effect of the electronic artificial larynx.
Owner:SUZHOU BEHERZI MEDICAL TECH CO LTD

A diagnostic aid method for laryngeal paralysis combined with audio and video processing

The present invention proposes a laryngeal paralysis diagnosis auxiliary method combined with audio and video processing, comprising the following steps: obtaining an original laryngoscope video with audio information and video information; predicting the audio information through a keyword recognition model to extract an effective phonation segment, and obtaining a first laryngoscope segment corresponding to the effective phonation segment from the original laryngoscope video segment according to the matching relationship between the audio information and the video information; detecting and identifying the glottis area in the first laryngoscope segment, and segmenting the glottis area from the first laryngoscope segment; marking the glottis area and calculating the physical properties of the glottis area, the physical properties including one or more of the glottis area area, vocal cord opening and closing angle, and vocal cord width. The present invention uses a multimodal analysis method combined with audio and video to segment the laryngoscope video, extract key video segments, and provide a variety of objective evaluation indicators for doctors to refer to, thereby improving diagnostic efficiency and quality.
Owner:DUKE KUNSHAN UNIVERSITY +1

A soft, flexible and communicative device for patients with laryngectomy and its method thereof

PCT designated stageWO2025220035A1SensorsDiagnostic recording/measuringLaryngectomyAcoustics
The present invention relates to a soft, flexible, and communicative device for patients with laryngectomy and its method thereof The present invention discloses the fabrication of soft, lightweight, skin-compatible, and reusable device for silent speech interfaces (SSIs). It further comprises the unique feature to recognize speech-related information using surface electromyography (sEMG). sEMG-based speech recognition operates on signals recorded from a set of sEMG sensors that are strategically located on the face (with the help of desired form factor) and measure muscle activity associated with the phonation, resonation, and articulation of speech. sEMG sensors are printed onto strategical locations on soft, stretchable, and biocompatible membrane shaped into a form-factor of a face mask. The silent speech interfaces (SSIs) can also be deployed in acoustically challenging environment or where privacy / confidentially is a desirable such as in defense or military application and it is cost effective with reliable speech recognition accuracy of 96.2%(>95 %).
Owner:SHITASHII INNOVATIONS PTE LTD

Flexible liquid metal sensor and voiced / unvoiced speech recognition system

A flexible liquid metal sensor and a voiced / unvoiced speech recognition system. The flexible liquid metal sensor attached to the throat is configured to detect a hybrid-modal signal consisting of laryngeal low-frequency muscle movements and acoustic vibrations during voiced or unvoiced speech of a person. By designing discrete and continuous sensor layouts to accurately capture the frequency of laryngeal vibrations during phonation and spatial distribution characteristics of muscle movements, pressure information in different directions and at different positions is measured. Laryngeal data acquisition and filtering are achieved by means of a signal acquisition and analysis system, so as to construct a relational dataset between laryngeal acoustic-vibration hybrid-modal signals and expressed speech semantics. By establishing a deep neural network training model based on time-frequency features to train the relational dataset, the content expressed by a person during voiced or unvoiced speech can be recognized, thereby meeting the requirements of persons with speech impairments and the general population for conveying the expressed content in environments where speech is impaired.
Owner:CHINA ACAD OF LAUNCH VEHICLE TECH