184 results about "Normal voice" patented technology

The present invention eliminates the disadvantages of an analysis target used by a cellular phone and speech recognition, that is, a normal sound which is transmitted through the air and which is externally sampled through a microphone, and improves the disadvantages that noise may be mixed or occur in the target, that information may leak, and that corrections are difficult. The present invention also provides a personal portable information terminal realizing new portable terminal communications which do not require training and which conform to the cultural practice of human beings. In the present invention, no apparatus that obtains an analysis target is put off human body, and a normal sound is not an analysis target. A stethoscope-type microphone is installed on the surface of the human skin. Then, a vibration sound is sampled which is obtained when a non-audible murmur articulated in association with speech action (the motion of the mouth) not using the regular vibration of the vocal cords is transmitted through the flesh. A vibration sound obtained when a non-audible murmur amplified is transmitted through the flesh is similar to a whisper. The vibration sound can thus be heard and understood by human beings. Accordingly, the vibration sound can be used for a speech over the cellular phone as it is. Further, when the vibration sound obtained when the non-audible murmur is transmitted through the flesh is analyzed and converted into parameters, a kind of soundless recognition is realized. The present invention replaces the HMM model, conventionally used for speech recognition by an acoustic model created on the basis of a vibration sound obtained when a non-audible murmur is transmitted through the flesh. Therefore, the present invention provides a new method of inputting data to the personal portable information terminal.

The invention discloses a method and system for detecting abnormal use of voice input equipment. A characteristic extracting mode which is more comprehensive to remote voice signal characteristics and closer to human perception is adopted in the invention so as to roughly judge background voice, normal voice and remote voice. On the basis of classification of audio signals, by adopting the combined method of a modern signal processing technology and a statistical machine learning theory, the problem of multiple limits on front-end voice input by a traditional method is overcome so that signal-level quality scoring is closer to human scoring. According to the invention, the difference problem of front-end input voice quality due to artificial use errors of the equipment in large-scale tests of spoken language is solved.

This invention satisfies a need for exchanging video between two wireless terminals over a new 4G network. It would be impractical to design the service to operate over existing 2G and 3G networks. These older networks exhibit lack of throughput needed for extensive videophone service since they were originally designed for voice service.This invention will employ the new 4G network to allow a terminal to select the proper bandwidth needed to send either voice only or video and voice over the same wireless connection.Use of class of service characters combined with the receiving terminal address sent by the originating terminal will allow the wireless carrier to process the call as a video to video call by accessing a “caller ID” table distinct from the normal voice “caller ID” table. The new originating “caller ID” will be selected from this table and forwarded to the receiving terminal causing it to enter video mode automatically and to use a distinctive ring tone.

The invention discloses a voice characteristic identification-based silence detecting method, firstly extracting multi-threshold overzero rate of an audio data frame; pre-identify silence by weighting the multi-threshold overzero rate to identify obvious silence; extracting composite characteristic of an audio data frame, where the composite characteristic comprises overzero rate, short-time energy value, and variable resolution frequency spectrum-based Mel scale revere spectrum coefficient; using dichotomy support vector machine to identify the composite character of the audio frequency, one class normal voice and the other class silence. And the invention can raise success rate of silence detection and can identify some special voices, able to be widely applied to network voice talking, especially voice chatting and video meeting.

The invention discloses an automatic dustproof device used for shielding a voice outlet of electronic equipment. The automatic dustproof device comprises a shell. The voice outlet is formed in the shell. The shell is provided with a window corresponding to the voice outlet. The automatic dustproof device further comprises a coil and a shielding piece used for shielding the window. The shielding piece at least comprises a working face and a side face. The working face is provided with a plurality of magnets. The side face is provided with a telescopic piece. According to the automatic dustproof device and method, the shielding piece is automatically opened and closed, it is effectively ensured that the voice outlet is shielded before a voice diaphragm works and is rapidly opened when the voice diaphragm works, normal voice generation of the voice outlet is not affected, the problem that the voice outlet is exposed to the air in daily use is solved, dust particles are effectively prevented from being adsorbed to the surface of the voice diaphragm, the service life of the voice diaphragm is prolonged, and the using cost of the electronic equipment is reduced.

The invention discloses a device for eliminating echoes of mobile terminals, which comprises an echo canceller, an automatic gain controller and a noise suppression module, wherein the echo canceller is used for eliminating part of echo signals thereof according to the correlation between upstream signals and downstream signals and then sending output signals to the noise suppression module; the noise suppression module is used for receiving the output signals sent by the echo canceller, filtering noises of environment and residual noises not eliminated by the echo canceller and sending the output signals to the automatic gain controller; the automatic gain controller is used for comparing the downstream signals with the output signals sent by the noise suppression module in real time to conclude a decrement and adding the decrement to the upstream signals to eliminate the residual echoes thereof. The device for eliminating echoes of mobile terminals of the invention solves the problem of destroying normal voice signals when eliminating echoes, such as too great voice attenuation, changes of operation mode into simplex, discontinuous voices, distortion and so on.

Provided is a system and method for sending a “voice message” to a recipient without any intervention of a network. A user initiates a Short Voice Message (SVM) service (or short voice messaging) function and records a voice message within a device. The user sends the recorded voice message through a normal voice call. During a call setup, the recipient decodes a received call setup message and recognizes the call as a voice message. The recipient sets parameters for recording the voice message. Upon completion of the call setup, the user sends the recorded voice message directly to the recipient. The recipient records the voice message and stores the voice message in an inbox. Thus, the user can be provided with an option for directly sending a voice message without text typing or a text-to-voice conversion technique.

The invention discloses a method of converting whispered voice into normal voice based on a radial group neutral network, which comprises two steps of training and converting: respectively extracting line spectrum pair parameters of the whispered voice and the normal voice when in training; seizing mapping relation of spectrum envelope of the whispered voice and the normal voice by using the radial group neutral network; preprocessing the whispered voice when in conversion and extracting the line spectrum pair parameters, converting the line spectrum pair parameters of the whispered voice by the trained radial group neutral network, at last generating a driving source of the voice by using basic frequency mean value of the voice as basic voice frequency, and converting into the normal voice by a line spectrum pair synthesizer. The whispered voice converted by the invention achieves better effect on the respects of intelligibility threshold and tone quality.

The invention discloses a smart home control system and method compatible with non-normal voice. The system includes a voice analysis module, an identification module, a decision fusion module, a matching module, an interactive feedback module, a control module and an online learning module. The voice analysis module extracts the acoustic features of voice. The identification module identifies voice using a corresponding identification model. The decision fusion module carries out decision fusion using a voting strategy based on weighted grading. The matching module matches the output result of decision fusion with preset modes. The interactive feedback module gives different voice interactive feedback according to the output result of the matching module. The control module controls the working state of smart home equipment. The online learning module saves voice to a server by means of online learning. The system and the method are simple and practical. Identification and decision fusion are carried out using a corresponding voice template, and the voice template is updated by means of online learning. The voice identification rate and adaptability of the system are improved.

The invention provides a method, a device and a system for adjusting the coverage area of a base station. The method for adjusting the coverage area of the base station comprises the following steps of: acquiring a throughput rate of a sector; if the throughput rate of the sector is more than or equal to a heavy load threshold, acquiring a step value for adjusting downtilt or a transmitting power of an antenna of the sector according to signal quality data which is reported to the sector when a terminal switches the base state or according to a pre-stored reference data table; sending a first adjustment command which carries the step value to the base station to which the sector belongs, so that the base station can adjust the downtilt or the transmitting power of the antenna of the sector according to the step value after receiving the first adjustment command, and the coverage area of the base station is adjusted. By the method, the device and the system, the size of a coverage overlapping area of the base station and an adjacent base station is guaranteed, so that terminals which are positioned in the coverage overlapping area can enjoy normal voice service and data service, the phenomenon of unsuccessful switching or ping-pong switching is avoided, and the communication quality of the terminals in the coverage overlapping area is improved.

A mobile telephone for displaying graphically enhanced images. The mobile station has a display for displaying images as directed by a processor. At the user's request a displayed image will be graphically enhanced using an algorithm that takes into account audio inputs being received by the mobile station, either though its normal voice microphone or though another dedicated to this function. The audio input may also be input received previously and stored, and may have been received from another device for the purpose of sharing the visualization experience. The graphically enhanced image is displayed for the user's entertainment and changes as the audio input changes. The image itself may have been captured by the mobile station if it is capable of doing so, or it may have been received over the Internet or another network, or selected from a collection stored on the mobile station itself.

The invention relates to a network access authentication method and system of a satellite communication network. The method includes the following steps that: identity information of a satellite communication terminal is received; the identity information is verified automatically; and after the satellite communication terminal is verified successfully, corresponding communication resources are allocated to the satellite communication terminal, so that the connection of the satellite communication terminal and a communication satellite is shifted to a satellite service channel from a satellite signaling channel, and therefore, the satellite communication terminal can carry out normal voice or data communication. With the network access authentication method adopted, manual intervention is not needed, and respond to a communication requirement transmitted by the satellite communication terminal can be automatically completed, and resource allocation can be performed according to authentication results. Compared with an existing network access authentication mechanism, the method of the invention has much higher efficiency and can better meet ever-increasing satellite communication demands.

A method and system for providing a network which routes telephone calls to the dial-up access line of on-line data services, such as an Internet Service Provider. The calls are routed over, over data trunks to a circuit-switch that consolidates access to on-line data services. The data trunks are separate from trunks carrying normal voice telephone calls. At the originating office where the telephone call originates, the call is recognized as a call to a telephone number associated with the dial-up access telephone number of an on-line data service. A database selects a route over a data trunk to the terminating office having a circuit-switch that consolidates access to the on-line data services. The consolidation of access to on-line data services over segregated data trunks to a single circuit-switch reduces congestion in the network by relieving the network from handling a large volume of long duration telephone calls.

The embodiment of the invention provides a microphone switching method and a terminal, and relates to the technical field of electronic terminals. The problem that the terminal cannot perform normal voice communication when a main microphone in a plurality of microphones is abnormal in the prior art can be solved. The specific scheme is as follows: detecting whether a voice signal input by the main microphone in the plurality of microphones is abnormal, if detecting that the voice signal input by the main microphone is abnormal, setting a secondary microphone as the main microphone so as to perform the voice communication through the set microphone. The embodiment of the invention is used for performing the microphone switching.

A telecommunications system and method for routing Internet traffic without interfering with normal voice traffic on trunklines and circuits. This can be accomplished by implementing a "Traffic Route Control" functionality by local service providers to provide a method for managing and segregating Internet traffic so as to not interfere with voice traffic. In addition, with this "Traffic Route Control" functionality, a "Single Number Access" functionality service can be provided to the ISPs, in which a single 800 number accesses and routes calls to the closest local access number. Furthermore, a "Traffic Statistics" functionality can be introduced as a service to the ISPs to provide a WEB-based interface, which allows ISPs to collect, retrieve, print, view and / or transfer statistical information on traffic patterns associated with their allocated trunklines.

The invention relates to a field of electronic technology and specifically relates to an awakening device and method. The voice activation detection based awakening device includes a microphone used for sensing sound signals and converting the sound signals to electric signals; a first signal extracting unit connected to the output terminal of the microphone and used for extracting base frequency signals in the output signals of the microphone; a comparison unit connected to the first signal extracting unit and comparing the base frequency signals with a reference base frequency range indicating voice features and generating a first comparison result; and a controller connected to a comparison unit and producing an awakening signal under the effect of the output signals of the comparison unit. According to the invention, the device can identify the distance of a sounder besides recognizing whether the voice signals are consistent to features of human voice or not, so that interference on normal voice activation detection due to irrelevant voice signals can be avoided and voice awakening can be realized effectively.

The invention provides a voice evaluation method and device. The voice evaluation method comprises the steps that voice data to be tested are received; voice recognition is conducted on the voice data to be tested to obtain voice recognition data; the voice recognition data are analyzed to defect whether the voice recognition data are abnormal voice data or not, and an evaluation result of the voice data to be tested is generated according to a detection result. The voice evaluation method can detect and recognize abnormal voice, so that abnormal voice is deleted from the voice to be tested, the abnormal voice can not join evaluation of normal voice, influence of the abnormal voice on the evaluation result is greatly reduced, the accuracy of the evaluation result is improved, the evaluation requirement of a user is met, and user experience is improved.

The invention discloses a DTW (dynamic time warping) voice recognition-based truck examining method which comprises the step of examining the truck by a training template and a voice recognition template. The method comprises the steps of: taking a DTW voice recognition algorithm as the core; forming the recognition template by training the normal voice generated when a normal truck passes through a track and the voice generated when a damaged truck passes through the track; distinguishing the condition of the damaged parts of the truck during recognition; and transmitting a result to a control center, so that an early diagnosis and forecast process can be made, and the running security of the truck can be guaranteed. The DTW voice recognition-based truck examining method has the advantages of being high in fault detection and recognition rate, and simple in operation system.

The invention relates to the communication field and particularly relates to a method for eliminating noise of VOIP system bidirectional duplex hand-free voice. According to the method, through modes of dynamic sampling modeling, non speech frame peeling and linear noise voice frame attenuation, conversation noise is dynamically and timely inhibited, normal voice signals can not be attenuated through the method, hardware cost does not increase, and user experience is greatly improved.

A method for providing prompt information to mobile communication device by mobile communication network includes launching voice calling to called switchboard by calling terminal, returning called terminal state information back to calling terminal and special dressing ring platform (SDRP) by called switchboard, launching connection to SDRP by calling terminal for requesting to provide information and providing information to calling terminal by SDRP. An other method includes launching normal voice calling to called terminal by calling terminal and launching connection to SDRP by calling terminal for requesting to provide information, providing said information to calling terminal by SDRP and returning called terminal state information back to calling switchboard by called switchboard. The third method is also disclosed.

An abnormal sound detection device includes a first learning unit that inputs a normal operating sound of the machine equipment, and registers a normal sound base spectrum from an amplitude spectrogram, a new sound / new vibration extraction unit that executes supervised nonnegative matrix factorization (NMF) using the normal sound base spectrum as teacher data on an acoustic signal input during diagnosis, and outputs a nonnegative matrix not allowed to be approximated with a low rank in the normal sound base spectrum, a second learning unit that extracts a new sound / new vibration component from the normal operating sound of the machine equipment, learns a normal sound model from the new sound / new vibration component, and registers the normal sound model, and an abnormality detection unit that computes a probability that the new sound / new vibration component extracted from the acoustic signal of the machine equipment during diagnosis is generated from the normal sound model.

The invention discloses an abnormity detection method and device for voice data. The abnormity detection method comprises the steps that firstly target voice data transmitted through an uplink call path is acquired; the normal voice data includes a large portion of low-frequency energy and a small portion of high-frequency energy, so that whether the high-frequency energy in the target voice datais less than the high-frequency energy in the normal voice data or not can be judged through analyzing the size of the low-frequency energy or high-frequency energy in the target voice data; and whenthe judgment result is yes, it indicates that the high-frequency energy in the target voice data is lost or truncated, so that the target voice data can be determined to be abnormal.

The invention provides an ill-conditioned voice evaluation method based on Chinese voice, which comprises the following steps: completing automatic alignment of input continuous voice signals and corresponding texts by using an automatic Chinese voice recognition system, and completing phoneme segmentation; segmenting the continuous voice signal into vowels, clear consonants and turbid consonantsaccording to the time sequence of phoneme segmentation, and then extracting features; wherein the extracted features form a feature parameter set, and the feature parameter set is screened by a feature selector and then input into a classifier to obtain a fine score of the voice problem. According to the method, a large-scale normal voice database is used for training an automatic voice recognition system; the segmented voice sequences are classified according to the sounding characteristics of different phonemes, the characteristic parameters are designed for different phoneme types, finally,the objective overall score and each detailed score for the voice problem are obtained, and an important reference is provided for clinical diagnosis and rehabilitation treatment.

The invention discloses a method for defending an inaudible instruction to control a voice assistant based on machine learning. The method comprises the following steps: 1) acquiring the data of positive and negative samples, 2) performing data segmentation on the positive and negative sample data; 3) performing sample feature selection and normalization; 4) selecting a classifier for training andgenerating a detection model used for detecting a malicious voice command; and 5) detecting the voice command to be detected through the obtained detection model. According to the invention, a creative feature selection method is selected, and the method is directed to intelligent devices with different models, and a normal voice command and the malicious voice command need to be acquired throughthe intelligent devices of the type, and a specific classifier for the type of device is trained as positive and negative samples. Through the customized mode, the problem that the detection and defense cannot be carried out by cross devices can be well solved.

The invention discloses a fault positioning method and device of communication network. The method mainly comprises that communication signaling among network elements is monitored, call records are generated and the percent of completed voice calls is calculated according to the monitored communication signaling, and the call records comprise the network elements, which the voice call passes successively, at least; if the percent of completed voice call is lower than a set threshold, according to failure reasons of the call records in which voice connection fails, the proportions of failure calls caused by the different reasons are determined, the failure reason of the highest frequency is selected from the failure reasons, whose proportions of failure calls are greater than the proportion of failure calls in normal voice connection, as the first failure reason, and all calling records in connection failure caused by the first reason are selected from the calling records in voice connection failure to form fault positioning decision sets; and intersection sets are selected from the fault positioning decision set, and the last network element of the intersection sets is determined to be the fault network element. The method can be used to position the fault network element rapidly.

The invention provides a pluggable mobile terminal voice calling method. The method comprises the following steps: after a wireless communication module is inserted into an external application module, the wireless communication module performs communication rate matching with the external application module; the wireless communication module receives an AT command which initiates a call request and is sent by the external application module, and the initiated call request comprises a called number of a called party; the wireless communication module establishes voice channel connection with a base station by an air interface according to the called number, and receives successful connection instruction information sent by the base station; the wireless communication module returns an AT command controlled and instructed by a service report to the external application module according to the successful connection instruction information, and performs the voice communication with the called party. In the method, after the wireless communication module is spliced with the external application module and the rate matching is performed, the wireless communication module is responsible for establishing the communication connection with a wireless network, providing a voice channel for a user to perform the voice communication and ensuring the normal voice communication functions of the mobile terminal.

Three-way call detection is an important component of correctional facility telephone equipment because it helps restrict calling access by certain persons to certain restricted telephone numbers. Various three-way call detection methods exist, but all of these implementations suffer from one major limitation—the detection accuracy is not as high as is desired by the industry. The present invention improves detection accuracy, using “steganography.”Steganography involves hiding one set of data or signals within another signal or carrier in such a way that its presence is virtually imperceptible to the end recipient, and potential even the originator of the carrier signal. Television producers use steganographic methods to encode data in video signals for security, distribution monitoring, piracy-control, and other reasons. The present invention involves a device that connects to a telephone, either at the line or handset interfaces, and produces a known signal that is steganographically hidden within the user's normal voice signal. Detection equipment, residing at another location, monitors signals on telephone calls and tests for the presence of the hidden signal or data generated by the invention. Once detection is achieved, appropriate action, such as terminating or recording the call, may be taken. Improved accuracy is achieved by choosing the appropriate hidden signal(s)—ones that never occur in the course of normal conversation and never get generated by telephone company equipment. Once detected, the presence of the signal guarantees the call was made to the restricted party from a particular phone line.