77 results about "Voice Treatment" patented technology

Coding of received audio signals and the resulting application of electrical stimuli applied to electrodes used in a cochlear implant system are disclosed together with a method of fitting this new coding strategy. One of the aims is to place specific stimulation representing pitch by applying near threshold electrical stimuli with limited and focussed excitation fields. A range of stimulation rates and a minimal range of current levels above threshold are used for creation of a dynamic loudness percept for a cochlear implant recipient. Another aim is to disclose a coding scheme based on a model of physiological measures (i.e. refractoriness, adaptation, spread of activation field, spatiotemporal acoustical cochlear activation patterns and spontaneous activity) to estimate the proportions of available excitable auditory neurons close to the electrodes available for stimulation. The spectral bands formed from the pre-processing of incoming audio signals are weighted by these proportions of excitability to control place, timing, rate and current level of electrical stimuli applied to the electrodes available in the array.

A system for presenting a recorded message on behalf of an agent receiving a call at an agent station in a call center, the agent station having a telephony interface for receiving calls and a personal computer with a video display unit (PC / VDU), has a telephony switching apparatus enhanced by a computer-telephony integration (CTI) processor, an Interactive Voice Response (IVR) system executing a voice treatment option (VTO) software, coupled to the telephony switching apparatus and the CTI processor; and a data repository having recorded messages stored on behalf of the agent and accessible to the CTI processor. The CTI processor routes incoming calls to the telephony interface for the agent, uses data associated with the calls for selecting appropriate recorded messages, and causes, by controlling the IVR, a retrieved recorded message to be played to a caller upon the agent picking up the routed call. The system is useful with both conventional telephone systems and data network telephony, such as over the Internet.

The embodiment of the invention discloses a voice interaction method, a voice interaction device and voice interaction equipment, and belongs to the field of voice treatment. The method comprises the following steps: determining sound source directions according to awakening signals which are respectively received by two microphones, wherein the awakening signals are the signals which are preset and are used for awakening the voice interaction equipment to work; receiving voice signals through the two microphones directionally according to the sound source directions; performing noise reduction processing on the voice signals, performing voice identification and semantic analysis of the voice signals which are subjected to noise reduction processing through an identification model, and generating corresponding interaction data; executing corresponding interaction operation according to the interaction data. According to the embodiment of the invention, the cost of the voice interaction equipment is reduced on the premise of ensuring the voice identification accuracy; difficulties and complexity in signal processing are reduced, so that the voice interaction rate is improved.

The sound processor and method uses a model of basilar membrane motion to select stimuli, based upon the predicted motion which the acoustic signal presented would produce in an acoustically excited normally hearing cochlea. The filter; used, in contrast to single channel per electrode approaches, cover multiple channels and overlap with each other. Consequently the stimuli presented produce a neural excitation pattern which approximates the spatio-temporal travelling wave observed on the basilar membrane in an acoustically excited normally hearing cochlea. Preferably, the predicted electrode stimuli are based upon the instantaneous predicted amplitude of the electrode location.

An exemplary method of fitting a sound processor to a cochlear implant patient includes pre-loading program data representative of a plurality of sound processing programs onto a sound processor during a data transfer session and selectively using, after completion of the data transfer session, one or more of the pre-loaded sound processing programs to fit the sound processor to the patient. Corresponding methods and systems are also described.

An exemplary system includes 1) an electro-acoustic stimulation (“EAS”) sound processor configured to be located external to a patient, 2) a cochlear implant communicatively coupled to the EAS sound processor and configured to be implanted within the patient, 3) an electrode array communicatively coupled to the cochlear implant and configured to be located within a cochlea of the patient, and 4) a receiver communicatively coupled to the EAS sound processor and configured to be in communication with an ear of the patient. The EAS sound processor directs at least one of the cochlear implant and the receiver to apply stimulation to the patient, records an evoked response that occurs in response to the stimulation, and performs a predetermined action in accordance with the evoked response. Corresponding systems and methods are also disclosed.

The embodiment of the invention discloses a method of processing telepresence conference user signals, which comprises: getting the signing in information of telepresence conference place and recognizing the free subscriber area according to the signing in information of users; making sure the signals from the free subscriber area are invalid signals and the signals from the other subscriber areas are valid signals. The invention also provides device and system thereof. According to the invention, in telepresence applied occasions, attending situation of users in each subscriber area can be recognized according to the simple and convenient signing in device arranged on the terminal side. And according to the information, in the processes of video switching, screen composing and acoustic processing, the invalid video and audio code stream can be effectively and automatically wiped off so as to improve the performance, efficiency and usability of conference system.

An exemplary system includes an implantable cochlear stimulator configured to be implanted within a patient, a sound processor communicatively coupled to the implantable cochlear stimulator and configured to direct the implantable cochlear stimulator to generate and apply electrical stimulation to one or more stimulation sites within a cochlea of the patient, and a displacement sensor assembly configured to measure a displacement of the stapedius of the patient that occurs in response to the application of the electrical stimulation and transmit displacement data representative of the measured displacement to the sound processor. Corresponding systems and methods are also disclosed.

The embodiment of the invention discloses a method and a device for maintaining voice business continuance and a communication system. The method comprises the steps of: obtaining a terminal requirement for voice switching by an MME (Mobile Management Entity); acquiring a voice treatment mode adopted by a terminal needing switching in a source network; and initiating voice bearing switching to a target network by adopting a voice treatment mode adopted by the terminal. The invention ensures that a network side can acquire the voice treatment mode adopted by the terminal, thereby initiating the voice bearing switching process to the target network by the voice treatment mode adopted by the terminal, maintaining the continuance of the voice business, and improving the user experience.

The invention discloses a cleft palate voice glottal stop automatic identification algorithm and device, relates to the technical field of voice analysis and identification, and aims to provide a glottal stop automatic identification method and device. A computer is adopted for automatically identifying cleft palate voice glottal stops, effective and objective auxiliary diagnosis is provided to patients and voice teachers, and wide popularization of cleft palate voice assessment and voice treatment is facilitated. According to the technical key points of the invention, the method comprises the steps of: 1, collecting voice signals of syllables to be tested; 2, carrying out initial and final division on the voice signals of syllables, and retaining initial voice signals; 3, extracting characteristic values of the initial voice signals; and 4, sending the characteristic values into trained identification models, wherein the identification models judge whether glottal stops exist in the voice signals of syllables according to the characteristic values.

An auditory sense training device 1 to be used in an auditory sense training method for training auditory sense by listening to a sound formed by processing an original sound comprises a band attenuation processing method 20 for attenuating a predetermined frequency band of an original sound 10, a switching means 30 for selectively outputting either the original sound or the output from said band attenuation processing means, a panpot processing means 40 for performing a panpot process wherein a voice signal formed by attenuating an original sound of one channel is superposed to the original sound of another channel, and a phase reverse processing means 50 for performing a phase reverse process of reversing the phase of the original sound, wherein a trainee listens to the original sound and a band attenuation processed sound formed by attenuating a predetermined frequency band of the original sound alternately.

Systems and method for performing adaptive audio signal processing using music as a measurement stimulus signal. A musical stimuli generator may be used to generate musical stimulus signals composed to provide a stimulus with a spectrum that is substantially dense, and ideally white or pink, over a selected frequency range, so that all frequencies of interest are stimulated. The musical stimuli generator may generate melodically pleasing musical stimulus signals using music clips that include any of: a chromatic sequence, a chromatic sequence including chromatic tones over a plurality of octaves, a chromatic sequence including chromatic tones over a selected plurality of octaves, or an algorithmically composed chromatic sequence, to cover a selected frequency range. The musical stimulus signal may be generated as sound into the environment of use. An audio input picks up the sound from the environment, and a sound processor uses the received musical stimulus signal to determine a transfer function.

A headphone system includes sound processor which calculates properties of the environment from signals from an internal microphone and an external microphone. The impulse response of the environment may be calculated from the signals received from the internal and external microphones as the user speaks.

The invention relates to an electric cochlear external voice treatment device, comprising microprocessor and power circuit. The input end of microprocessor is connected to acoustic frequency interface, output end is connected to radio frequency mode; said microprocessor employs digital signal processor TMS320VC5509A, the acoustic frequency interface employs TLV320AIC23B, the digital signal processor is connected with acoustic frequency interface through interface of I2C and MCBSP, the digital signal processor TMS320VC5509A is outer connected with FLASH memory, said FLASH memory stores systematic program for electric cochlear external voice treatment device. The kernel processor employs TMS320VC5509A, which increases system computing ability and reduces power consumption. The employed single chip acoustic frequency decoder accomplishes functions of enlargement, resisting aliasing filtering and AD sampling, which simplifies hard construction for whole flat base and reduces cost in further.

The invention discloses a method, a system and a device for adjusting the rotating speed of radiating equipment in data processing equipment. The method comprises the following steps: after radiating control is started, a voice collection device collects environmental voice information and sends the environmental voice information to a voice processing device; the voice processing device processes the environmental voice information to obtain an environmental noise decibel value and sends the environmental noise decibel value to a rotating speed adjusting device; meanwhile, a temperature acquiring device acquires a temperature value to be compared inside the data processing equipment and sends the temperature value to be compared to the rotating speed adjusting device; the environmental noise decibel value, the temperature value to be compared and a preset threshold value are compared, and whether to generate a control command or not is judged according to the comparing result, if so, a control command is generated, and the rotating speed of the radiating equipment is adjusted according to the control command.

The invention provides a method for operating a game based on dimensional sounds. The method comprises the following steps that (10) one or more original sounds needed by the game are firstly recorded or synthesized, then sound processing software is adopted for carrying out left and right channel volume matching or channel reversal or high and low frequency volume adjustment on the original sounds, and sound fragment files in all directions are generated; (20) the generated sound fragment files in all the directions are added into a file of the game; (30) a main game program plays sound fragments in the directions to be operated in the game process according to game operating logic, and a user operates a controller according to the directions of the played sound fragments. The method has the advantages that the two eyes of the user are freed, and the user can play the game without staring at a mobile phone or a computer display screen for a long time; the game based on the dimensional sounds is easy and convenient to operate, and suitable for being played in working clearances to achieve the relax aim, and work efficiency is improved by alternating work with rest.

An exemplary sound processor (104) included in an auditory prosthesis system includes 1) a clock facility (406) configured to detect an elapsing of a predetermined amount of time and 2) a fitting facility (408) communicatively coupled to the clock facility and configured to automatically perform, in response to the elapsing of the predetermined amount of time, one or more fitting operations with respect to the auditory prosthesis system. Corresponding systems and methods are also disclosed.

The invention discloses a voice recognizing network delay optimizing method. The method includes the steps of conducting voice treatment on currently-recorded voice signals to obtain voice recognizingdata, and inputting the voice recognizing data to a cache; obtaining a preset duration of voice recognizing data from the cache, wherein the preset duration has an initial duration value; conductingdecoding treatment on the preset duration of voice recognizing data to obtain corresponding decoded voice recognizing data; parsing the decoded voice recognizing data to obtain a semantic parsing result, and judging whether the semantic parsing result can express a complete semantic meaning or not; if yes, outputting the semantic parsing result. By means of the method, decoding can be conducted while speaking instead of being conducted after the sentence ends in the past, and the rapid and good effects are achieved.

The invention discloses a stored-grain pest sound detection identification system, including a first sound collection module, a sound pretreatment module, a sound processing module, a retrieval contrast module, a drawing module, a regression calculating module, a prediction analysis module and a database. The database is connected with a second sound collection module, an image collection module, a man-machine operation module, a data processing module and a correlation establishing module. The invention completes pest detection through identifying insect sounds, achieves real-time, accurate and lossless automatic detection of pests in stored grain, and can predict the multiplying condition of pests, thereby facilitating pest treatment measure making and reducing economic loss caused by delayed discovery and delayed treatment.

An exemplary method of fitting a cochlear implant patient includes a fitting station detecting a user input associated with a sound processor of a cochlear implant system, wherein the sound processor is communicatively coupled to the cochlear implant fitting station by way of a communication path, and transmitting a signal to the sound processor by way of the communication path in response to the detecting of the user input, the signal configured to direct the sound processor to display a visual cue. Corresponding methods and systems are also described.

The invention relates to equipment for fitting a hearing aid to the specific needs of a hearing impaired individual. The equipment comprising a computer or similar device with soft-ware, where the device has display means for visual display of data, data entry means for entering hearing aid programming data into the device, data storing means, and data output means for outputting programming data to the hearing aid. According to the invention means are provided for selecting simultaneous settings relating to two or more different parameters relating to the processing of sound in the hearing aid to be programmed.

The sound processor and method uses a model of basilar membrane motion to select stimuli, based upon the predicted motion which the acoustic signal presented would produce in an acoustically excited normally hearing cochlea. The filter; used, in contrast to single channel per electrode approaches, cover multiple channels and overlap with each other. Consequently the stimuli presented produce a neural excitation pattern which approximates the spatio-temporal travelling wave observed on the basilar membrane in an acoustically excited normally hearing cochlea. Preferably, the predicted electrode stimuli are based upon the instantaneous predicted amplitude of the electrode location.

The sound processing device, set between a sound source and a loud speaker and used for processing the sound output from the sound source and outputting it to the loud speaker, comprises: a selector for selecting an singing- exercising mode or a normal mode; an original sound eliminating mode for attenuating the human sound frequency in the audio signals output by the sound source under singing-excising mode and a tone regulation mode for regulating the tone of the audio signals output from the sound source under singing-excising mode. Advantage: raised convenience and amusement for the user of excising singing.

The invention discloses a baby crying sound translation method based on sound feature recognition. According to crying sound characteristic differences of babies in different physiological states, crying sound characteristic parameters of babies in different physiological states are extracted respectively by using a computer sound processing technology, wherein the crying sound characteristic parameters are 16 characteristic parameters including 11 characteristic parameters: the tone, pitch, loudness, energy, frequency and frequency co-occurrence matrix; on the basis of a BP neural network algorithm, crying sound sections of the babies in different physiological states are collected, denoising and filtering are carried out on the sound sections, a correspondence relationship between baby crying sound characteristic differences and six kinds of physiological states including hunger, drowsiness, pain, boredom, fear and discomfort is established, and identification results of hunger, drowsiness, pain, boredom, fear and discomfort are provided. In the trained BP neural network, characteristic parameters extracted from any baby crying sound section are inputted and thus an identification result is obtained from the output layer, so that the baby care quality and efficiency are improved and the erroneous determination and delayed determination in baby caring are reduced.

A method of automatic announcer voice removal from a televised sporting event. A sound processing circuit divides an audio input signal of a televised sporting event into multiple audio segments. The audio input signal includes crowd noise and announcer commentary. If an audio segment does not exceed a pre-defined amplitude threshold, a voice removal utility adds the audio segment to a recent crowd noise library and stores the segment in an output buffer. If the amplitude of a segment exceeds the threshold, the utility adds the segment to a recent announcer voice library. The sound processing circuit generates an attenuated version of the segment and blends the attenuated version with one or more mixed segments from the recent crowd noise library. The voice removal utility stores the attenuated and blended segment in the output buffer and outputs one or more audio segments from the buffer in a chronological order.

The invention discloses a digital auditory integrated training system, which comprises a signal source, a power supply, a host and a signal receiving device, the host is electrically connected with the power supply, the signal source is connected with the host by a signal line, and the signal receiving device is communicated and connected with the host. The digital auditory integrated training system of the invention can correct the disorder phenomena of the auditory system on the voice treatment and stimulate the cerebral cortex by listening to a group of music after filtration and modulation, thus achieving the purpose of improving behavior disorders and emotional disorders. The digital auditory integrated training system is safe and reliable, the treatment has no side effects which are serious and existed for a long time, and the digital auditory integrated training system is applicable to: pervasive developmental disorder (PDD), including autism (Infantile Autism) and Asperger syndrome; attention deficit hyperactivity disorder (ADHD); special speech and language developmental disorder (SLD); emotion disorder (ED); learning disorder (LD) and so on.