98 results about "Speech sounds" patented technology

Chat categorization uses semi-supervised clustering to provide Voice of the Customer (VOC) analytics over unstructured data via an historical understanding of topic categories discussed to derive an automated methodology of topic categorization for new data; application of semi-supervised clustering (SSC) for VOC analytics; generation of seed data for SSC; and a voting algorithm for use in the absence of domain knowledge / manual tagged data. Customer service interactions are mined and quality of these interactions is measured by “Customer's Vote” which, in turn, is determined by the customer's experience during the interaction and the quality of customer issue resolution. Key features of the interaction that drive a positive experience and resolution are automatically learned via machine learning driven algorithms based on historical data. This, in turn, is used to coach / teach the system / service representative on future interactions.

A method for utilizing oral movements is used in speech assessment, speech therapy, language development, and controlling external devices. A device is used which includes a sensor plate having sensors to detect contact of the tongue with the sensor plate. One aspect of the invention allows viewing representations of contact of the tongue and palate during speech and comparing the representations with model representations displayed in a split screen fashion. The model representations may be generated by another speaker utilizing a sensor plate or by computer generated representations which have been electronically stored. The representations may be analyzed to assess speech proficiency and the model may be mimicked for speech enhancement.

A phonics training system provides immediate, audible and virtual answers to questions regarding various images such as objects, animals and people, posed by a user when the user views such images on a video display terminal of the system. The system can provide virtual answers to questions without the need for an instruction or teacher and includes a computer having a video output terminal and an electronic library containing common answers to basic questions. This system can also include an artificial intelligence system.

The present invention relates to systems and methods for enhancing the holistic and temporal speech perception processes of a learning-impaired subject. A subject listens to a sound stimulus which induces the perception of verbal transformations. The subject records the verbal transformations which are then used to create further sound stimuli in the form of semantic-like phrases and an imaginary story. Exposure to the sound stimuli enhances holistic speech perception of the subject with cross-modal benefits to speech production, reading and writing. The present invention has application to a wide range of impairments including, Specific Language Impairment, language learning disabilities, dyslexia, autism, dementia and Alzheimer's.

The invention consists of a method and computing system for recording and analyzing the voice which allows a series of parameters of phonation to be calculated. These transmit relevant information regarding effects caused by organic disorders (which affect the physiology of the larynx) or neurological disorders (which affect the cerebral centers of speech). The classification methods are also considered an essential part of the invention which allow estimations of the existing dysfunction to be obtained and for the allocation of personality. The usefulness of the invention lies in the possibility of applying the dysfunction estimation in primary care service centers for patient screening to specialist care centers, simplifying examination protocols, saving costs and reducing waiting lists. This methodology can also be used for detecting the personality of a speaker by their voice, allowing access to installations or services.

The invention provides an electronic larynx speech reconstructing method and a system thereof. The method comprises the following steps of: firstly, extracting model parameters form collected speech as a parameter library; secondly, collecting the face image of a sounder, and transmitting the face image to an image analysis and processing module to obtain the sounding start moment, the sounding stop moment and the sounding vowel category; thirdly, synthesizing a voice source wave form through a voice source synthesizing module; and finally, outputting the voice source wave form through an electronic larynx vibration output module. Wherein the voice source synthesizing module is used for firstly setting the model parameters of a glottis voice source to synthesize the glottis voice source wave form, then simulating the transmission of the sound in the vocal tract by using a waveguide model and selecting the form parameters of the vocal tract according to the sounding vowel category so as to synthesize the electronic larynx voice source wave form. The speech reconstructed by the method and the system is closer to the sound of the sounder per se.

A phonics training system provides immediate, audible and virtual answers to questions regarding various images such as objects, animals and people, posed by a user when the user views such images on a video display terminal of the system. The system can provide virtual answers to questions without the need for an instruction or teacher and includes a computer having a video output terminal and an electronic library containing common answers to basic questions. This system can also include an artificial intelligence system.

The invention relates to a glottal wave analog type artificial electronic throat with personal characteristics, in particular to a real glottal wave analog type artificial electronic throat with personal characteristics, which comprises a wave shape generating and processing system with the characteristics of amplitude and frequency jitter, a power amplifying circuit 18 and a miniature electricity-force conversion system 19, wherein the electricity-force conversion system 19 can be regulated and controlled. The invention has a working form that: the wave shape generating and processing system can store glottal wave shapes with personal sounding characteristics; a wave shape generating module 12 generates initial glottal waves according to the stored glottal waves; an amplitude jitter module 14 adds amplitude jitter, and a frequency jitter generating module 13 adds frequency jitter; the generated wave shapes are converted into analog signals through a digital-to-analogue conversion module 17; the output signal wave shapes are converted into mechanical vibration by the electricity-force conversion device 19 after power amplification; the mechanical vibration is applied to the neck of a patient to generate glottal waves; and the glottal wave shapes are modulated by the tongue, the nasal cavity, the oral cavity, the lip, and other organs of the patient to form voice outside the lip. A wave shape frequency regulating module 15 and a wave shape amplitude regulating module 16 are respectively applied to the wave shape generating module 12 so as to regulate frequency and amplitude.

The invention discloses a classroom data analysis method and a system. The method comprises the following steps: obtaining classroom data in the classroom, wherein the classroom data comprises face data, student behavior data, teacher behavior data and teacher voice data; analyzing the classroom according to the classroom data. The invention adds a data acquisition mode, enriches the data types, supports classroom behavior analysis, face recognition, speech recognition, etc., and carries out trend analysis and score / behavior prediction on the data of the class and the students, and carries outpersonalized recommendation according to the trend analysis and the score / behavior prediction of the class and the students. Through a variety of sources of classroom data collection, the method andsystem can carry out accurate analysis and detailed evaluation of the classroom, can help managers to make effective decisions, teachers precision teaching, students personalized learning.

The present invention provides an Internet based system and method for monitoring the location of a subject at any time via telephone voice verification. The system and method enables an agency officer to enroll a subject's profile into a computerized system. The subject then responds to a series of verbally answered questions, the responses to which are utilized to establish a voice signature for the subject. Subsequently, the system and method automatically and periodically contacts the subject at pre-determined locations at pre-determined times to verify the subject's actual presence at the locations via voice verification software. The present invention also enables the agency officer to monitor and review compliance efforts implemented by the Internet based system while also providing notifications of non-compliance by the subject to the agency officer under criteria previously established by the officer.

Using various embodiments, methods, systems, and apparatuses are disclosed for capturing the behavior of living subjects, where the data can be processed by a machine-learning algorithm to control an autonomous robot. In one embodiment, using the data captured by a user performing everyday operations, the autonomous robot can behave in a substantially similar manner as the living subject did in the environment where the behavior capture sessions of the living subject were carried out. Further, once the autonomous robot is provided with the processed data, the actions of the robot can iteratively be stored and processed by the machine learning algorithm to further refine the robot's movements performing the everyday operations. In another embodiment, behavior recorded from the living subject can be processed such that the autonomous robot is able to speak and understand spoken speech similar to that which occurred most frequently in the behavior capture sessions.

The invention provides an electrolaryngeal speech reconstruction method and a system thereof. Firstly, model parameters are extracted from the collected speech as a parameter library, then facial images of a speaker are acquired and then transmitted to an image analyzing and processing module to obtain the voice onset and offset times and the vowel classes, then a waveform of a voice source is synthesized by a voice source synthesis module, finally, the waveform of the above voice source is output by an electrolarynx vibration output module, wherein the voice source synthesis module firstly sets the model parameters of a glottal voice source so as to synthesize the waveform of the glottal voice source, and then a waveguide model is used to simulate sound transmission in a vocal tract and select shape parameters of the vocal tract according to the vowel classes.

The present invention provides a speech intention expression system including a sensor part which is adjacent to one surface of the head and neck of a speaker and measures physical characteristics of articulators, a data interpretation part which grasps articulatory features of the speaker on the basis of the position of the sensor part and the physical characteristics of the articulators, a data conversion part which converts the position of the sensor part and the articulatory features to speech data, and a data expression part which expresses the speech data to the outside, wherein the sensor part includes an oral tongue sensor corresponding to the oral tongue.

The invention discloses a three-dimensional virtual image lip shape generation method and device and electronic equipment. The method comprises the following steps: voice data are obtained, expression parameters and posture parameters are obtained according to the voice data, the expression parameters represent expression information of a lip, the posture parameters represent mouth shape information, and a three-dimensional virtual image lip shape is generated according to the expression parameters and the posture parameters. According to the method and the device, the problem of how to improve the synchronization degree and the naturalness of three-dimensional virtual lip shape generation in the prior art is solved.

The invention relates to the technical field of realizing operation on a control terminal by virtue of oral actions, by a human-computer interaction device capable of identifying tongue movement action, tooth occlusion action and oral breathing action. The human-computer interaction device disclosed by the invention is compact in structure, high in control accuracy and sensitivity, low in error, and convenient to carry and use. According to the human-computer interaction device disclosed by the invention, the limitations and defects of limb control and voice intelligent identification control technologies are solved, and substitution and supplement effects are acted on the original technology for operating the control terminal. According to the human-computer interaction device disclosed by the invention, the degree of participation of the disabled people in social activities is increased, and the disabled people can control use terminals more and better, so as to obtain convenient service brought by human development; the disabled people can also increase own employment opportunities by controlling the use terminals. The human-computer interaction device disclosed by the invention also has an efficiency-increasing function, the both hands can be released to perform other operations or get a rest time during the use of the human-computer interaction device, and then the hand resources are allocated and utilized better to achieve the efficiency-increasing function.

The invention relates to a vocal cord-larynx ventricle-vocal track linked physical model and a mental pressure detection method. The physical model includes a mechanical equation set for describing a vocal cord motion model, and an aerodynamics equation set for describing pressure drop distribution in a glottis depth direction and a larynx ventricle-false vocal cord-vocal track direction. A physiological parameter estimation algorithm is designed through the established vocal cord-larynx ventricle-vocal track linked physical model, so that a physiological variation mechanism of phonation in a pressure state is researched. Physiological feature parameters of the vocal cords and the larynx ventricle when a speaker phonates in the pressure state are extracted, and a relation from real voice signals to physiological features is established. According to the estimated physiological parameters, variation features of various vocal organs and the flow state of airflow in the vocal organs under the influence of pressure variation factors are obtained, and the variation features are used for detection of the mental pressure. The detection recognition precision and reliability are improved.

The invention discloses a voice method and system capable of promoting auditory language cerebral cortex development of a premature infant. The voice method comprises the steps: S1, pure heart sound and mixed sound of the heart sound and voice of a mother of the premature infant are recorded; S2, the recorded sound is saved and processed to form intrauterine environment sound; and S3, the intrauterine environment sound saved in a cloud server is obtained and played. The voice method and system capable of promoting auditory language cerebral cortex development of the premature infant have the function of creating the uterine environment sound, a familiar intrauterine sound environment is created for the premature infant, and auditory language cerebral cortex development of the premature infant can be promoted.

A patient interface of a respiratory therapy system is provided, and comprises: a. a mask body; b. a mask seal secured to the mask body and configured to form a seal with the user's face, at least around the user's mouth; the mask body and mask seal being arranged to define an interior breathing chamber of the patient interface; and c. an inlet to the breathing chamber configured to receive a flow of breathable gases into the breathing chamber. To assist in allowing a user to speak clearly whilst wearing / using the patient interface, a user actuatable speech valve is provided on the patient interface and is operable to selectively occlude and open a speech flow path from the breathing chamber to atmosphere when the user wishes to speak.

A pronunciation learning support system of the present invention comprises the steps of: acquiring at least one part of recommended air current information data including information on an air current flowing through an inner space of an oral cavity and recommended resonance point information data including information on a location on an articulator where a resonance is generated, during vocalization for a pronunciation corresponding to each subject to be pronounced; and providing an image by processing at least one of a process for displaying specific recommended air current information data corresponding to a specific subject to be pronounced, in the inner space of the oral cavity in an image being provided on a basis of a first perspective direction and a process for displaying, at a specific location on the articulator, specific recommended resonance point information data corresponding to the specific subject to be pronounced.

The invention discloses an adaptive navigation voice broadcast method, device and system. The method includes: a navigation voice broadcasting terminal obtains the basic navigation information and sends the basic navigation information to an operation and control platform; the operation and control platform obtains the navigation scene sequence according to the basic navigation information, obtains a configuration file according to the navigation scene sequence, and sends the configuration file to the navigation voice broadcasting terminal; the navigation voice broadcasting terminal obtains areplacement broadcast audio which is obtained according to a basic broadcast copy and a voice broadcast strategy; the navigation voice broadcasting terminal obtains contents to be broadcast of the current navigation scene and obtains a target audio from the replacement broadcast audio according to the contents to be broadcast; and the navigation voice broadcasting terminal plays the target audio.The invention supports the replacement of speech sound materials in any link of the whole navigation process, so as to provide better driving safety guidance and improve user viscosity.

The embodiment of the invention discloses a method and device for demodulating reverberation of audio signals. The method comprises the steps of acquiring first and second audio reverberation signalswhich are acquired from an audio channel, wherein the first audio reverberation signals are acquired from M frequency points in a current frame, and the second audio reverberation signals are acquiredfrom M frequency points in a historical frame; according to the first and second audio reverberation signals, updating N frequency points in the M frequency points on the basis of a room regression coefficient corresponding to the historical frame to obtain a room regression coefficient corresponding to the N frequency points in the current frame, and configuring known numerical values accordingto a room regression coefficient corresponding to (M-N) frequency points in the M frequency points (except the N frequency points) in the current frame; obtaining a pure voice signal corresponding tothe current frame according to the room regression coefficient corresponding to the M frequency points in the current frame.

The invention discloses a protective bag used in a severe environment. Protective clothing and a protective hood which are worn in a matched mode are included. The protective hood comprises an integrally-formed hood, a face mask and a neck connecting portion connected to a bottom of the hood. The neck connecting portion is connected with the protective clothing to form a completely sealed head wearing space. The hood is connected with an oxygen system. A camera system and a voice system are arranged on the face mask. The face mask comprises an eye visual window and a nose and mouth space whichare matched with a face of a human body, a silica gel isolation strip is arranged between the nose and mouth space and the eye visual window, the silica gel isolation strip is arranged on a nose bridge of the human body and is matched with the shape of the nose bridge, and the silica gel isolation strip divides the eye visual window and the nose and mouth space into two relatively isolated spaces. By using the protective bag used in the severe environment, a problem that in the prior art, after rescue and epidemic prevention workers wear isolation equipment, sights are blocked due to an influence of exhaled carbon dioxide and moisture is solved.

The invention comprises systems and methods for the assessment of mental state by means of analysis of key words or phrases written or spoken by a subject. These elements are detected for instance through use of a smartphone app and / or bespoke software keyboard, and their occurrence is logged and analyzed, either locally or remotely. Text and speech may both be analyzed for purposes of the invention, which analyzes key words / phrases for example in terms of their emotional or psychological content, for example counting expressions of positive or negative feelings, attitudes, or other categories. By analysis of frequency of such usages, an estimate or reflection of mental state of the typist is built. Diagnosis of various conditions may thus be carried out, especially by watching how the frequencies and / or percentages of such key elements change over time.

The invention relates to a Uygur language phoneme-viseme parameter conversion method and system, and belongs to the technical field of voice-human face animation information processing. The method comprises the steps: adding 41 features and the visibility features of teeth and a tongue, carrying out the clustering of vowel mouth shape data, and obtaining a vowel basic static viseme set; respectively carrying out the clustering of consonants and mouth shape data combined with different vowels, and obtaining a consonant basic static viseme set; proposing a composite viseme concept based on the above, and building a Uygur language basic dynamic viseme set; giving a composite dynamic viseme model and a dynamic viseme model parameter estimation method based on a linear regression algorithm, thereby achieving the Uygur language phoneme-viseme conversion. According to the invention, the method carries out the text analysis of a to-be-converted Uygur language text according to the basic dynamic viseme set and the model parameters thereof, obtains a basic dynamic viseme sequence in the text, and can generate a human face and lip portion visual voice animation consistent with the content of the text.

We invented (a) a teaching method of European language pronunciation (the English language included), as well as (2) a system of representation of European language sounds. We discovered that European language speakers resonate sound primarily in the throat, while Asian speakers do so primarily in the mouth (THE THROAT LAW) and based on this discovery we invented a way to condition one's throat to pronounce like native speakers of European languages. We also invented a way to represent how to read syllables and how to connect syllables, capitalizing on our discovery of how native speakers read them (THE 3-BEAT LAW). Our system of representation can be used to build a reading assistance devise, such as electronic dictionary.

The invention relates to a domestic and medical two-purpose sound recording and fetal heart sound listening stethoscope, and belongs to the field of medical apparatuses. A stethoscope head (1), a sound conduction tube, a three-way tube and a listening tube protecting port are mutually connected, so that a pipeline stethoscope is constituted; a microphone, an amplifier (2), a recording-playing module (3), a transmission module (4), a power supply and the like are arranged in the stethoscope head, so that an electronic stethoscope, which is capable of recording and playing sound, is formed to listen two different stethoscopic sound effects. People can identify sounds from left side and right side through two ears, but the known stethoscopes are operated in a mode of communicating left and right ears, and subsequently, a listening habit is changed and a hearing threshold is narrowed; with the application of the stethoscope which adopts a novel dual-sound-track circuit, the listening habit is recovered and the hearing threshold is widened, so as to bring about benefits for doctors in auscultation. In addition, known fetal heart rate instruments cannot output original heartbeat sound, while by virtue of the novel stethoscope, actual fetal heartbeat sound can be listened, and meanwhile, the sound can be recorded or played; and when the sound is recorded, a voice catalog can be additionally annotated by virtue of the microphone, so that functions of searching and tracing an electronic medical record can be developed. Moreover, a carotid artery plaque detection method is more convenient and rapider than the known stethoscopes.

The invention discloses a hidden washbasin, comprising a washbasin body and a washbasin base placeable inside the washbasin body and partially hidable in a wall. Slides are disposed symmetrically on two inner sides of the inside of the washbasin base. Rollers matching with the slides are disposed on two sides of the washbasin body. A luminous decorative plate is disposed at the front end of the washbasin body. The washbasin base is provided with a voice-operated switch enabling the opening or closing of the luminous decorative plate to be controlled. When the washbasin is idle, the washbasin body may be pushed into the washbasin base and collected like a drawer; when a passer-by is near this switch, the voice-operated switch may be activated by footsteps, speech sound and claps, and thus the luminous decorative plate is electrified to emit light, displaying a pattern thereon and giving decoration.

The invention provides an audible and visual alarm with classified voices for mines. The alarm comprises a base, a lamp cover, a supporting member, a suspension ring, a wire outlet, a cover plate and a circuit device. The circuit device comprises a main circuit board, a horn and five light-emitting diode (LED) circuit boards. The horn and the five LED circuit boards are all electrically connected with the main circuit board. The circuit device performs flashing alarm and voice alarm simultaneously according to received alarm trigger signals. The circuit device is fixedly mounted on the base through the supporting member, and the lamp cover is fixedly connected with the base in a sealing mode. The suspension ring and the wire outlet are both mounted on the base. The cover plate is magnetically attracted on a base board of the base. Each of the LED circuit boards is provided with 4 to 12 high-brightness red LEDs and 4 to 12 of high-brightness green LEDs. According to the audible and visual alarm with classified voices for mines, the shatter and shock resistance is good, and the alarm light is 360-degree visible; the voice alarm voice quality is good, no noise exists, and alarm contents are convenient to edit; and the alarm trigger signals can be combined and arranged in a classified mode, and the voice alarm can be controlled remotely.