9312 results about "Voice data" patented technology

A method and system used to determine the similarity between an input speech data and a sample speech data is provided. First, the input speech data is segmented into a plurality of input speech frames and the sample speech data is segmented into a plurality of sample speech frames. Then, the input speech frames and the sample speech frames are used to build a matching matrix, wherein the matching matrix comprises the distance values between each of the input speech frames and each of the sample speech frames. Next, the distance values are used to calculate a matching score. Finally, the similarity between the input speech data and the sample speech data is determined according to this matching score.

A method and system are provided for text-to-speech synthesis with personalized voice. The method includes receiving an incidental audio input (403) of speech in the form of an audio communication from an input speaker (401) and generating a voice dataset (404) for the input speaker (401). The method includes receiving a text input (411) at the same device as the audio input (403) and synthesizing (312) the text from the text input (411) to synthesized speech including using the voice dataset (404) to personalize the synthesized speech to sound like the input speaker (401). In addition, the method includes analyzing (316) the text for expression and adding the expression (315) to the synthesized speech. The audio communication may be part of a video communication (453) and the audio input (403) may have an associated visual input (455) of an image of the input speaker. The synthesis from text may include providing a synthesized image personalized to look like the image of the input speaker with expressions added from the visual input (455).

A communication-status notification apparatus enabling a subscriber to observe various kinds of communication status in a network easily via the subscriber's own terminal in a communication system. The apparatus includes a request analysis section for discriminating whether or not voice data received by gateway equipment from a subscriber terminal contains a request on monitoring / controlling or notifying of a communication status in the network and for analyzing the content of the request when contains, a communication-status monitor / control section for monitoring / controlling the communication status responsive to the content of the request analyzed by the request analysis section based on a processing status of the voice data in the gateway equipment, and a communication-status notification section for notifying the subscriber terminal of the communication status monitored / controlled by the communication-status monitor / control section via the gateway equipment responsive to the content of the request analyzed by the request analysis section. The apparatus is useful when applied to VoIP gateway equipment or the like used for a VoIP communication system.

A problem to be solved is to robustly detect a pronunciation variation example and acquire a pronunciation variation rule having a high generalization property, with less effort. The problem can be solved by a pronunciation variation rule extraction apparatus including a speech data storage unit, a base form pronunciation storage unit, a sub word language model generation unit, a speech recognition unit, and a difference extraction unit. The speech data storage unit stores speech data. The base form pronunciation storage unit stores base form pronunciation data representing base form pronunciation of the speech data. The sub word language model generation unit generates a sub word language model from the base form pronunciation data. The speech recognition unit recognizes the speech data by using the sub word language model. The difference extraction unit extracts a difference between a recognition result outputted from the speech recognition unit and the base form pronunciation data by comparing the recognition result and the base form pronunciation data.

A synthetic speech system includes a phoneme segment storage section for storing multiple phoneme segment data pieces; a synthesis section for generating voice data from text by reading phoneme segment data pieces representing the pronunciation of an inputted text from the phoneme segment storage section and connecting the phoneme segment data pieces to each other; a computing section for computing a score indicating the unnaturalness of the voice data representing the synthetic speech of the text; a paraphrase storage section for storing multiple paraphrases of the multiple first phrases; a replacement section for searching the text and replacing with appropriate paraphrases; and a judgment section for outputting generated voice data on condition that the computed score is smaller than a reference value and for inputting the text after the replacement to the synthesis section to cause the synthesis section to further generate voice data for the text.

A system improves speech recognition includes an interface linked to a speech recognition engine. A post-recognition processor coupled to the interface compares recognized speech data generated by the speech recognition engine to contextual information retained in a memory, generates a modified recognized speech data, and transmits the modified recognized speech data to a parsing component.

A method for real-time speaker recognition including obtaining speech data of a speaker, extracting, using a processor of a computer, a coarse feature of the speaker from the speech data, identifying the speaker as belonging to a pre-determined speaker cluster based on the coarse feature of the speaker, extracting, using the processor of the computer, a plurality of Mel-Frequency Cepstral Coefficients (MFCC) and a plurality of Gaussian Mixture Model (GMM) components from the speech data, determining a biometric signature of the speaker based on the plurality of MFCC and the plurality of GMM components, and determining in real time, using the processor of the computer, an identity of the speaker by comparing the biometric signature of the speaker to one of a plurality of biometric signature libraries associated with the pre-determined speaker cluster.

A client device incorporates partial speech recognition for recognizing a spoken query by a user. The full recognition process is distributed over a client / server architecture, so that the amount of partial recognition signal processing tasks can be allocated on a dynamic basis based on processing resources, channel conditions, etc. Partially processed speech data from the client device can be streamed to a server for a real-time response. Additional natural language processing operations can also be performed to implement sentence recognition functionality.

One or more methods and systems of effectively transmitting voice and voice band data from one node to another are presented. In one embodiment, the system comprises an NTP time server generating absolute times to computing devices such as residential voice over internet protocol (VoIP) gateways. The NTP time server generates absolute times in response to NTP time requests made by one or more computing devices such as residential VoIP gateways. In one embodiment, the method comprises determining an adequate rate for requesting absolute times from an NTP server, making periodic requests to the NTP server, obtaining the absolute times from the NTP server, and generating an adjustment parameter for use by a computing device such as a residential VoIP gateway.

A power line communication system communicating over a medium voltage power line including a VoIP endpoint that transmits voice data and requests to establish a voice connection to a medium voltage (MV) access device is provided. The medium voltage access device may determine a response to the request, allocate voice data packets a higher priority than general data packets, and transmit the data packets over the MV power line according to their priority. The MV access device may provide one or more voice over internet protocol (VoIP) switch functions and, in response to the requests, grant or deny the requests based, for example, on the number of established voice connections.

Disclosed are an apparatus for recognizing voice using multiple acoustic models according to the present invention and a method thereof. An apparatus for recognizing voice using multiple acoustic models includes a voice data database (DB) configured to store voice data collected in various noise environments; a model generating means configured to perform classification for each speaker and environment based on the collected voice data, and to generate an acoustic model of a binary tree structure as the classification result; and a voice recognizing means configured to extract feature data of voice data when the voice data is received from a user, to select multiple models from the generated acoustic model based on the extracted feature data, to parallel recognize the voice data based on the selected multiple models, and to output a word string corresponding to the voice data as the recognition result.

A conference support system includes a data reception portion for receiving image data of attendants in a conference and voice data, an emotion distinguishing portion for distinguishing emotions of attendants in accordance with the image data, a text data generation portion for generating comment text data that indicate contents of speeches of the attendants in accordance with the voice data, and a record generation portion for generating record data that include contents of a speech of an attendant and emotions of attendants when the speech was made, in accordance with emotion data that indicate a result of distinguishing made by the emotion distinguishing portion and the comment text data.

Apparatus and methods are provided for multiplexing application flows over a pre-allocated bandwidth reservation protocol session. According to one embodiment, a pre-allocated reservation protocol session, such as an RSVP session, is shared by one or more application sessions. The reservation protocol session is pre-allocated over a path between a first network device associated with a first user community and a second network device associated with a second user community based upon an estimated usage of the path for application sessions between users of the first and second user communities. Subsequently, the one or more application sessions are dynamically aggregated by multiplexing application flows associated with the one or more individual application sessions onto the pre-allocated reservation protocol session at the first network device and demultiplexing at the second network device. According to another embodiment, a network device enables multiple applications, such as VoIP applications, that require real-time performance to share an aggregated reservation protocol session, such as an RSVP session. The network device includes a storage device having stored therein one or more routines for establishing and managing the aggregated reservation protocol session. A processor coupled to the storage device executes the one or more routines to pre-allocate the aggregated reservation protocol session and thereafter share the aggregated reservation protocol session among multiple application sessions of individual application sessions. The aggregated reservation protocol session is pre-allocated based upon an estimate of the bandwidth requirements to accommodate the multiple application sessions. The aggregated reservation protocol session is shared by multiplexing, onto the aggregated reservation protocol session, outbound media packets (e.g., packetized voice data) originated by local application / endpoints associated with the application sessions, and demultiplexing, from the aggregated reservation protocol session, inbound media packets (e.g., packetized voice data) originated by remote application / endpoints.

A voice-controlled data system may include a data storage unit including media files having associated file identification data, and a vocabulary generating unit generating phonetic data corresponding to the file identification data, the phonetic data being supplied to a speech recognition unit as a recognition vocabulary, where one of the media files may be selected according to a recognized speech control command on the basis of the generated phonetic data, where the file identification data include a language identification part for identifying the language of the file identification data, and where the vocabulary generating unit generates the phonetic data for the file identification data of a media file based on its language identification part.