164 results about "Quality voice" patented technology

The present invention provides a system and method for a reliable, low-cost, secure Internet Protocol (IP) based network that provides broadband-based voice communications as well as video and data communications. The IP network is arranged to function with the infrastructure of the Public Switched Telephone Network (PSTN), to control telephone calls in SS7 type networks and to provide the features, applications, and services of the typical SS7 networks in a voice over IP network. The present invention supports large effective call volumes, allows accommodation of a wide range of broadband-based service platforms, provides flexibility to support current and future calling feature services, and provides high quality voice transmission.

A system and method of bypassing the regulated portion of the Public Switching Telephone Network (PSTN) to establish carrier-grade voice transmissions and / or IP data communications between an Internet Calling Person having a first telephone and a first PC coupled to a first Local Service Access Provider (LSAP) and an Internet Called Party having a second telephone and a second PC coupled to a second different Local Service Access Provider (LSAP).

Certain aspects of a method and system for providing wireless communication may include a single integrated circuit (IC) that handles communication for at least a Bluetooth (BT) connection and a Wireless Local Area Network (WLAN) connection by controlling transmission of acknowledgement signals based on a measured voice quality for one or both of the BT connection and the WLAN connection. The transmission of the acknowledgement signals communicated from the mobile station to an access point may be controlled. A BT priority signal may be asserted if data to be transmitted comprises high quality voice (HV3) data. The transmission of the acknowledgement signals may be controlled by raising a priority of an asserted WLAN priority signal higher than a priority of the asserted BT priority signal. The voice data may be transmitted via high quality voice (HV3) frames over the BT connection based on the asserted WLAN priority signal.

A method and apparatus for establishing traffic priorities in an IP network connected with multiple communication sources is disclosed. Different types of packets such as voice packets and data packets are received for transmission over a single network access link. In order to assure quality voice transmissions, voice packets are given priority over data packets by limiting a transmission rate from a data input queue whenever voice packets are detected in a voice input queue. Different combinations of interleaved voice and data packets help to alleviate packet congestion while maintaining priority for voice packets. In one aspect of the invention, priority for voice packets is further accomplished by limiting the size of data packet frames. In some instances when no voice packets are awaiting transmission, data packets are transmitted at a maximum rate in order to make full use of the network access link bandwidth. The invention is particularly beneficial when implemented over cable and DSL network access links with slow upstream feed rates.

A novel protocol for an ad-hoc, peer-to-peer radio network that provides collision-free channel access with an emphasis on improving geographic reuse of the frequency spectrum. The protocol of the invention is executed on the reservation or control channel, and provides a method for allocating data transactions on the data channels. The system of the invention utilizes multiple parallel data channels that are coordinated by a single reservation channel. The transceiver of the system employs two modems to solve the channel reliability issues with multiple channel designs, where one is dedicated as a receive-only modem for gathering channel usage information on the reservation channel. High quality voice, video and data may be transmitted. The reservation channel implements a time division multiple access algorithm with dynamic slot allocation. In a distributed manner, nodes determine geographic reuse of slots based on channel quality extracted from the modem. Signal quality calculations are used to determine the likelihood of a slot reuse causing destructive interference within a node's neighborhood. Requests for slot usage are compared with the known traffic pattern and accepted or rejected by nodes within RF signal range based on the signal quality calculations.

The embodiment of the invention discloses a microphone-array speech-beam forming method, which comprises a digital-signal converting step, a frequency-region signal-obtaining step, a time-delay obtaining step, a time-delay compensating step and a weighted stacking step, wherein time-delay estimation based on phase conversion is adopted particularly in the time-delay obtaining step, thereby a beam-forming signal pointed to a target sound-source spatial position after enhancement processing is obtained. Compared with the prior art, the positioning precision and the directivity of a three-dimensional space are enhanced, the long-distance sound-picking capability in a complicated acoustics environment is greatly enhanced, high-quality voice signals are obtained, and noise and other interferences are reduced. The embodiment of the invention also discloses a speech-signal processing device and a system.

A novel protocol for an ad-hoc, peer-to-peer radio network that provides collision-free channel access with an emphasis on improving geographic reuse of the frequency spectrum. The protocol of the invention is executed on the reservation or control channel, and provides a method for allocating data transactions on the data channels. The system of the invention utilizes multiple parallel data channels that are coordinated by a single reservation channel. The transceiver of the system employs two modems to solve the channel reliability issues with multiple channel designs, where one is dedicated as a receive-only modem for gathering channel usage information on the reservation channel. High quality voice, video and data may be transmitted. The reservation channel implements a time division multiple access algorithm with dynamic slot allocation. In a distributed manner, nodes determine geographic reuse of slots based on channel quality extracted from the modem. Signal quality calculations are used to determine the likelihood of a slot reuse causing destructive interference within a node's neighborhood. Requests for slot usage are compared with the known traffic pattern and accepted or rejected by nodes within RF signal range based on the signal quality calculations.

A method for concealing lost frame includes: using history signals before the lost frame that corresponds to a lost MDCT coefficient to generate a first synthesized signal when it is detected that the MDCT coefficient is lost; performing fast IMDCT for the first synthesized signal to obtain an IMDCT coefficient corresponding to a lost MDCT coefficient; and using the IMDCT coefficient corresponding to the lost MDCT coefficient and an IMDCT coefficient adjacent to the IMDCT coefficient corresponding to the lost MDCT coefficient to perform TDAC and obtain signals corresponding to the lost frame. An apparatus for concealing lost frame is also disclosed herein. The method and the apparatus for concealing lost frames in the embodiments of the present invention make full use of the received partial signals to recover high-quality voice signals and improve the QoS.

A hands-free loudspeaker system which is capable of achieving high-quality voice amplification without requiring a human speaker to move to a microphone or a microphone to be moved to a human speaker. A microphone whose input level has continued to be above a threshold value for not shorter than a predetermined time period is detected, based on input signals from dispersedly arranged microphones. An input signal from the microphone is selected and outputted to each loudspeaker at an output level or with a delay time, according to a location of the loudspeaker. A preset lowest threshold level is initially set to the threshold value, and an input level of the microphone higher than the threshold value is newly set to the same, while when the input level is lower than the threshold value, a lower value is set to the same in a step-by-step manner.

A clear, high quality voice signal with a high signal-to-noise ratio is achieved by use of an adaptive noise reduction scheme with two microphones in close proximity. The method includes the use of two omini directional microphones in a highly directional mode, and then applying an adaptive noise cancellation algorithm to reduce the noise.

A telephone system and a voice encoding / decoding method capable of reducing the consumed power by reducing the memory capacity of buffer and generating high-tone-quality voice. The system writes an input voice frame to an input buffer and eliminates the delayed disturbance in a voice signal from the input voice frame based on the output voice frame to execute echo-canceling, and decodes the received voice packet data, so that the boundary of input voice frames can be set before the boundary of output voice frames, at least, for the time necessary for the echo-canceling and decoding. Thereby, the output voice frame can always be written at the same time as the input voice frame written to the input buffer and the delayed disturbance in the voice signal can be eliminated from the input voice frame based on the output voice frame and, thus the high-tone-quality voice can be generated.

A method and apparatus for a voice transcoder that converts a bitstream representing frames of data encoded according to a first voice compression standard to a bitstream representing frames of data according to a second voice compression standard using perceptual weighting that uses tuned weighting factors, such that the bitstream of a second voice compression standard to produce a higher quality decoded voice signal than a comparable tandem transcoding solution. The method includes pre-computing weighting factors for a perceptual weighting filter optimized to a specific source and destination codec pair, pre-configuring the transcoding strategies, mapping CELP parameters in the CELP parameter space according to the selected coding strategy, performing Linear Prediction analysis if specified by the transcoding strategy, perceptually weighting the speech using with tuned weighting factors, and searching for adaptive codebook and fixed-codebook parameters to obtain a quantized set of destination codec parameters.

The present invention relates to a transmitting apparatus, a transmitting method, a receiving apparatus, a receiving method, a transceiver, a communication apparatus and method, a recording medium, and a program in which high quality voice can be decoded. A cellular telephone 421-1 outputs coded voice data and also supplies uncoded voice sample data to a switching center 423 while a telephone call is not made. Based on voice data used for the previous calculation processing and newly input voice data, the switching center 423 performs calculation processing for quality-improving data for improving the quality of voice to be output from a cellular telephone 421-2 that receives the coded voice data. The switching center 423 stores the optimal quality-improving data as a user information database in association with the cellular telephone 421-1. The cellular telephone 421-2 decodes the coded voice data based on the optimal quality-improving data supplied from the switching center 423. The present invention can be applied to cellular telephones.

The invention provides a method and a system for eliminating multi-channel acoustic echo of remote voice frequency interaction. The method for eliminating the multi-channel acoustic echo of the remote voice frequency interaction comprises the following steps of: obtaining input multi-channel sound source acoustic signals; carrying out acoustic separation processing for the input multi-channel sound source acoustic signals; carrying out acoustic echo elimination processing for each-channel acoustic signals which are subjected to the acoustic separation processing through a self-adapting filter; combining and carrying out acoustic combination for the each-channel acoustic signals which are subjected to the acoustic echo elimination processing; outputting the acoustic signal which is subjected to the acoustic combination. The system comprises a DSP (Digital Signal Processor), a multi-channel acoustic separation combining device and a self-adapting filter module. According to the method and the system, provided by the invention, the multi-channel acoustic echo can be eliminated with lower cost, high-quality voice communication is supplied, the method and the system which are provided by the invention can be applied to various complicated remote voice bidirectional voice interaction fields, the smearing time for processing the echo can be increased to be 500 ms, the acoustic bandwidth is in the range of 20 Hz to 20 KHz, and the echo elimination ability is increased to be larger than 100 dB.

A clear, high quality voice signal with a high signal-to-noise ratio is achieved by use of an adaptive noise reduction scheme with two microphones in close proximity. The method includes the use of two omini directional microphones in a highly directional mode, and then applying an adaptive noise cancellation algorithm to reduce the noise.

The invention relates to computer voice inputting technology, in particular to a voice inputting method and a voice inputting device for converting speaking voice into relevant characters and mainly aims to provide a voice inputting method which can lower voice recognition error rate and has an intelligent recognition function. The voice inputting method comprises the following steps of: 1) acquiring voice made by a user by using a voice acquisition device; 2) filtering out noise in the acquired voice; 3) recognizing relevant characters according to a voice-character database; 4) correcting input characters according to an input context to obtain correct characters; and 5) displaying all obtained input characters or inputting all the obtained input characters into a file. The invention provides high-resolution and high-quality voice inputting technology for greatly lowering the voice inputting error rate of computers and other electronic devices, so that the way of inputting characters by voice can be accepted generally.

The invention discloses a voice conversion method based on adaptive Gaussian clustering under a non-parallel text condition, and belongs to the technical field of voice signal processing. The method comprises the steps: firstly carrying out the voice feature parameter alignment of non-parallel linguistic data through a method based on the combination of unit selection and sound channel length normalization; secondly carrying out the training of an adaptive Gaussian mixed model and bilinear frequency bending and amplitude adjustment, and obtaining a conversion function needed by voice conversion; finally achieving the high-quality voice conversion through the conversion function. The method overcomes the limit that the training stage requires the parallel linguistic data, achieves the voice conversion under the non-parallel text condition, is higher in adaptability and universality, employs the adaptive Gaussian mixed model to replace a conventional Gaussian mixed model, solves a problem that a Gaussian mixed model is not precise in voice feature parameter classification, combines the adaptive Gaussian mixed model with the bilinear frequency bending and amplitude adjustment, and is better in conversion personality similarity and voice quality.

Provided is are a method and device for processing a voice signal and achieving multi-party conversation, and a communication terminal. The method for processing the voice signal comprises steps of receiving a voice signal of at least one transmitting terminal; performing first audio processing on a first voice signal, wherein the first audio processing comprises at least one of automatic level control processing and sampling frequency converting processing, and the first voice signal is a voice signal selected from a to-be-transmitted voice signal acquired locally and a voice signal received locally, or a signal acquired by synthesizing at least two voice signals selected from the to-be-transmitted voice signal acquired locally and the received voice signal. The method may effectively solves problems of broken voice and plosive voice in multi-party conversation, achieves multi-party conversation between different sampling rates in a broadband and a narrowband, effectively guarantees a high-quality voice conversation effect in a three-party or multi-party conversation, achieves multi-party conversation without a value-added service of a network service provider, and is more convenient for a user to use.

The invention provides a session server, a user terminal and a method for controlling voice quality in a voice session. The session server comprises a determination module and a first processing module, wherein the determining module is used for determining whether a voice signal which is accessed to the voice session and inputted by a first user terminal is a low quality voice signal or not to obtain a determination result; and the first processing module is used for silencing the first user terminal or breaking the connection between the first user terminal and the voice session when the determination result indicates that the voice signal inputted by the first user terminal is the low quality voice signal. The session server, the user terminal and the method can effectively control the problem of low quality voice in the voice session.

The invention discloses a high-quality voice conversion method based on modeling of signal timing characteristics. The high-quality voice conversion method based on the modeling of the signal timing characteristics comprises the following steps: aiming at parallel data of a source and a target, considering modeling and tracing the timing characteristics of the source and the target, utilizing the hybrid Kalman filter, estimating structural parameters of a model under the criteria of expectation maximization, utilizing characteristic parameter set of mapping voice of the model and finally achieving a high-quality voice conversion effect. According to the high-quality voice conversion method based on the modeling of the signal timing characteristics, strong correlation between the voice signal parameters is fully utilized, a novel hybrid Kalman filter is constructed by means of a physical process that simulation parameters change with time and is used for a parameter mapping process of the voice conversion, a set of special conversion algorithm which associates the parameter of the Kalman filter with physical properties of a voice signal is designed, and therefore a conversion of personality traits of a speaker can be achieved.

A method for high quality voice communication over an IP network. The method is implemented using an IP network device. Voice communication quality of service is initiated through the transmission of a path message for the voice communication. The path message is configured for establishing a communications path through the nodes of the IP network. A reservation message is received in response to the path message. The reservation message is configured for specifying a range of voice streams for a bandwidth reservation, allowing a single reservation message to specify bandwidth for quality of service for multiple voice calls. The bandwidth reservation for the range of voice streams is implemented in accordance with the reservation message. The path message can be transmitted from an originating IP network device, such as an originating VoIP gateway, and can be generated by a first voice application executing thereon. The reservation message can be received from a terminating IP network device, such as a terminating VoIP gateway, and can be generated by a second voice application executing thereon. The reservation message includes a source port range specifying the range of voice streams for transmission. A bandwidth reservation table within the IP network device is updated in accordance with the reservation message, and bandwidth for transmission of the range of voice streams is reserved using the reservation table.

The invention discloses an STARWGAN-GP and x vector-based many-to-many speaker conversion method which comprises a training stage and a conversion stage. An STARWGAN-GP and an x vector are combined torealize a voice conversion system. According to the method, the X vector with higher characterization performance and practicability is added to characterize personalized features of a speaker, and WGAN-GP is used to replace GAN, so that the problems of unstable GAN training, gradient disappearing and the like are solved; a network with higher training stability and higher convergence speed is constructed, so that the personality similarity and the voice quality of a converted voice are further improved; a high-quality voice conversion method is implemented. The method can relieve the dependency on a parallel text and realize voice conversion under a non-parallel text condition, and also can further integrate a multi-source-target-speaker-pair conversion system into a conversion model torealize many-to-many speaker conversion.

The invention provides a method for encrypting voice based on the GSM voice channel transmission, which is applicable to the field of mobile communication. Through directly modulating encrypted voice data into voice-like coding signals conforming to the acoustic code coding format in the voice-like modulation process of the GSM sending end, the method can reduce once encoding and decoding of an acoustic code device. Even in the IP network, the signal transmission speed obtained by the method can meet the requirement of high quality voice secrecy communication.

Embodiments of the invention disclose a voiceprint recognition method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining frequency spectrum informationof a to-be-recognized voice; recognizing valid voice segments and invalid voice segments in the to-be-recognized voice according to the frequency spectrum information; removing the invalid voice segments, and splicing the valid voice segments to obtain a valid voice; acquiring frequency spectrum information of the valid voice; performing feature extraction on the frequency spectrum information ofthe valid voice through a feature extraction model based on a deep convolutional neural network to obtain a to-be-recognized voiceprint eigenvector corresponding to the to-be-recognized voice; and performing similarity calculation on the to-be-recognized voiceprint eigenvector and existing voiceprint eigenvectors in a voice feature library, and determining speaker identity information corresponding to the to-be-recognized voice. According to the embodiment of the invention, the invalid voice segments are removed, so that high-quality voice data are provided for the feature extraction model, and the accuracy of a voiceprint recognition result is improved.

The invention provides a specific continuous voice filtering method and device of a mobile phone, and belongs to the technical field of communication methods and equipment. When a user uses the function, user voice is recorded at first, identified specific voice is recorded in the mobile phone, and a voice library of the mobile phone is built; when the mobile phone is used for communication every time, the user can make the choice that the mobile phone only identifies the specific voice. By means of the specific continuous voice filtering method and device of the mobile phone, in a noisy communication environment, communication inconvenience occurring in the environment can be overcome effectively, and it can be guaranteed that the other party of the communication can obtain high-quality voice communication; certainly, when the function is used, only the voice of the user can pass through the mobile phone, voice of other people around the user cannot be transmitted to the other party, and high applicability is obtained in the aspect of user privacy protection.

The invention discloses a VOIP self-adaptation speech coding method and system and an SIP server. According to the VOIP self-adaptation speech coding method, the VOIP self-adaptation speech coding scheme comprises the steps that network available bandwidth is detected, the speech coding sequence is sequenced according to the detected network available bandwidth of the opposite terminal, the sequence is sent to the opposite terminal, and then both sides of a conversation select the respectively supported coding formats for carrying out speech coding on RTP streams according to the received speech coding sequence. According to the VOIP self-adaptation speech coding method, the SIP server only inquires the network available bandwidth of the opposite terminal of the initiator of SIP messages, after an SDP package modified according to the network available bandwidth of the opposite terminal of the SIP client side reaches the opposite terminal, the speech code suitable for the current network condition of the opposite terminal is selected preferentially, and therefore the optimal speech coding formats under the condition of the respective current network available bandwidth are used by the both sides of the SIP client side, the requirement for different kinds of bandwidth by different coding formats is met, and high-quality voice communication service is provided for users.

The invention discloses a noise reduction headset. The noise reduction headset comprises a left earphone, a right earphone and a noise reduction unit; each of the left earphone and the right earphoneincludes a headset housing, a main microphone and an auxiliary microphone located outside a human ear canal, and an internal microphone located inside the human ear canal; the main microphones and theauxiliary microphones pick up a first voice signal spread via air; and the noise reduction unit performs noise reduction on the first voice signal and then performs superimposition on the first voicesignal and a second voice signal picked up by the internal microphones and transferred by a human body to generate a to-be-sent signal. According to the noise reduction headset provided by the invention, by performing noise reduction processing on the first voice signal picked up by the main microphones and the auxiliary microphones and then superimposing the first voice signal with the low-frequency second voice signal picked up by the internal microphones, a high-quality voice signal is obtained.