Patents by Inventor Xufang Zhao
Xufang Zhao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20150302851Abstract: A method of recognizing continuous digits uttered by a speaker using an automatic speech recognition (ASR) system includes receiving continuous digits via a microphone as speech from a user; detecting that recognition of one or more of the continuous digits falls below a predetermined confidence threshold; prompting the user to identify the continuous digits using a body gesture; detecting the body gesture made by the user; and identifying one or more of the continuous digits based on the body gesture.Type: ApplicationFiled: April 18, 2014Publication date: October 22, 2015Applicant: General Motors LLCInventors: Gaurav Talwar, Xufang Zhao
-
Publication number: 20150264480Abstract: A method of processing audio received at a plurality of microphones in a vehicle includes receiving the audio as a first audio stream and second audio stream at respective first and second microphones that are positioned at different locations within the vehicle; creating a first digital time series and a second digital time series that represent the first audio stream and the second audio stream, respectively; calculating a delay that exists between the first audio stream and the second audio stream based on a cross-correlation of the first digital time series and the second digital time series; and processing the received audio using the calculated delay.Type: ApplicationFiled: March 13, 2014Publication date: September 17, 2015Applicant: GM Global Technology Operations LLCInventors: Gaurav Talwar, MD Foezur Rahman Chowdhury, Xufang Zhao
-
Publication number: 20150255063Abstract: A method of detecting vanity numbers using an automatic speech recognition (ASR) system includes wirelessly downloading data from a vanity number database into a vehicle; storing the uploaded data in an ASR model at the vehicle; and receiving speech input from a vehicle occupant at the vehicle; cross-referencing phonewords detected from the received speech with content from the ASR model.Type: ApplicationFiled: March 10, 2014Publication date: September 10, 2015Applicant: General Motors LLCInventors: Gaurav Talwar, John L. Holdren, Matthew J. Heger, Xufang Zhao
-
Publication number: 20150248881Abstract: A system and method of tuning speech recognition systems includes performing text-to-speech conversion of text data; detecting the accuracy of speech converted from text data; determining that the detected accuracy is below a predetermined threshold; recording a user recitation of the text data in response to the determination; and storing the user recitation in an exception database located at a vehicle.Type: ApplicationFiled: March 3, 2014Publication date: September 3, 2015Applicant: General Motors LLCInventors: John L. Holdren, Gaurav Talwar, Xufang Zhao
-
Publication number: 20150142428Abstract: According to an embodiment of the disclosure, there is provided a method of choosing a nametag using automatic speech recognition (ASR). The method includes receiving a spoken nametag via a microphone; performing a first speech recognition analysis on the spoken nametag; determining that the first speech recognition analysis outputs only handheld wireless device nametags; performing a second speech recognition analysis that excludes the handheld wireless device nametags stored at the handheld wireless device; and combining the results of the first speech recognition analysis and the second speech recognition analysis.Type: ApplicationFiled: November 20, 2013Publication date: May 21, 2015Applicants: GENERAL MOTORS LLC, GM GLOBAL TECHNOLOGY OPERATIONS LLCInventors: Xufang Zhao, Gaurav Talwar, Dipankar Pal, John L. Holdren
-
Publication number: 20150110287Abstract: A method for processing a plurality of audio streams at a computer system onboard a vehicle is provided. The method receives the plurality of audio streams from a plurality of locations within a vehicle; prioritizes each of the plurality of audio streams to obtain a prioritization result; and completes a task associated with each of the plurality of audio streams, according to the prioritization result.Type: ApplicationFiled: October 18, 2013Publication date: April 23, 2015Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLCInventors: JOHN L. HOLDREN, XUFANG ZHAO, GAURAV TALWAR
-
Publication number: 20150056951Abstract: A vehicle telematics unit and method of operating the same is provided. In one embodiment, a method includes storing an application access code provided from a telematics service user, initiating a call from a vehicle to the application, and receiving a request for the access code from the application during the call. Furthermore, the method includes determining that the application has requested the access code using a speech recognition function at the vehicle and sending the stored access code to the application based on the determination of the speech recognition function.Type: ApplicationFiled: August 21, 2013Publication date: February 26, 2015Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLCInventors: GAURAV TALWAR, RON M. HECHT, XUFANG ZHAO
-
Publication number: 20140337029Abstract: At least first and second microphones with different frequency responses form part of a speech recognition system. The microphones are coupled to a processor that is configured to recognize a spoken word based on the microphone signals. The processor classifies the spoken word, and weights the signals from the microphones based on the classification of the spoken word.Type: ApplicationFiled: May 13, 2013Publication date: November 13, 2014Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLCInventors: Gaurav TALWAR, Xufang ZHAO
-
Publication number: 20140316782Abstract: Methods and systems are provided for managing speech dialog of a speech system. In one embodiment, a method includes: receiving a first utterance from a user of the speech system; determining a first list of possible results from the first utterance, wherein the first list includes at least two elements that each represent a possible result; analyzing the at least two elements of the first list to determine an ambiguity of the elements; and generating a speech prompt to the user based on partial orthography and the ambiguity.Type: ApplicationFiled: April 19, 2013Publication date: October 23, 2014Inventors: Eli TZIRKEL-HANCOCK, Gaurav TALWAR, Xufang ZHAO, Greg T. Lindemann
-
Patent number: 8762151Abstract: Methods of automatic speech recognition for premature enunciation. In one method, a) a user is prompted to input speech, then b) a listening period is initiated to monitor audio via a microphone, such that there is no pause between the end of step a) and the beginning of step b), and then the begin-speaking audible indicator is communicated to the user during the listening period. In another method, a) at least one audio file is played including both a prompt for a user to input speech and a begin-speaking audible indicator to the user, b) a microphone is activated to monitor audio, after playing the prompt but before playing the begin-speaking audible indicator in step a), and c) speech is received from the user via the microphone.Type: GrantFiled: June 16, 2011Date of Patent: June 24, 2014Assignee: General Motors LLCInventors: John J. Correia, Gaurav Talwar, Xufang Zhao, Rathinavelu Chengalvarayan
-
Patent number: 8639508Abstract: A method of automatic speech recognition includes receiving an utterance from a user via a microphone that converts the utterance into a speech signal, pre-processing the speech signal using a processor to extract acoustic data from the received speech signal, and identifying at least one user-specific characteristic in response to the extracted acoustic data. The method also includes determining a user-specific confidence threshold responsive to the at least one user-specific characteristic, and using the user-specific confidence threshold to recognize the utterance received from the user and/or to assess confusability of the utterance with stored vocabulary.Type: GrantFiled: February 14, 2011Date of Patent: January 28, 2014Assignee: General Motors LLCInventors: Xufang Zhao, Gaurav Talwar
-
Publication number: 20140019135Abstract: A method of speech synthesis including receiving a text input sent by a sender, processing the text input responsive to at least one distinguishing characteristic of the sender to produce synthesized speech that is representative of a voice of the sender, and communicating the synthesized speech to a recipient user of the system.Type: ApplicationFiled: July 16, 2012Publication date: January 16, 2014Applicant: GENERAL MOTORS LLCInventors: Gaurav Talwar, Xufang Zhao, Ron M. Hecht
-
Patent number: 8532674Abstract: A method of operating a vehicle telematics unit includes determining the location of a vehicle equipped with a vehicle telematics unit; determining if telematics dialing software operated by the vehicle telematics unit includes a verbal dialing protocol used at the determined vehicle location; if not, identifying one or more verbal dialing protocols used at the determined location of the vehicle; requesting telematics dialing software that includes the one or more identified verbal dialing protocols; receiving the requested telematics dialing software from a central facility; and storing the received telematics dialing software at the vehicle.Type: GrantFiled: December 10, 2010Date of Patent: September 10, 2013Assignee: General Motors LLCInventors: Uma Arun, Rathinavelu Chengalvarayan, Kevin R. Krause, Eray Yasan, Gaurav Talwar, Xufang Zhao, Michael A. Wuergler
-
Publication number: 20130080172Abstract: A method of evaluating attributes of synthesized speech. The method includes processing a text input into a synthesized speech utterance using a processor of a text-to-speech system, applying a human speech utterance to a speech model to obtain a reference wherein the human speech utterance corresponds to the text input, applying the synthesized speech utterance to at least one of the speech model or an other speech model to obtain a test, and calculating a difference between the test and the reference. The method also can be used in a speech synthesis method.Type: ApplicationFiled: September 22, 2011Publication date: March 28, 2013Applicant: GENERAL MOTORS LLCInventors: Gaurav Talwar, Xufang Zhao
-
Publication number: 20120323577Abstract: Methods of automatic speech recognition for premature enunciation. In one method, a) a user is prompted to input speech, then b) a listening period is initiated to monitor audio via a microphone, such that there is no pause between the end of step a) and the beginning of step b), and then the begin-speaking audible indicator is communicated to the user during the listening period. In another method, a) at least one audio file is played including both a prompt for a user to input speech and a begin-speaking audible indicator to the user, b) a microphone is activated to monitor audio, after playing the prompt but before playing the begin-speaking audible indicator in step a), and c) speech is received from the user via the microphone.Type: ApplicationFiled: June 16, 2011Publication date: December 20, 2012Applicant: GENERAL MOTORS LLCInventors: John J. Correia, Rathinavelu Chengalvarayan, Gaurav Talwar, Xufang Zhao
-
Publication number: 20120245934Abstract: A method of automatic speech recognition. An utterance is received from a user in reply to a text message, via a microphone that converts the reply utterance into a speech signal. The speech signal is processed using at least one processor to extract acoustic data from the speech signal. An acoustic model is identified from a plurality of acoustic models to decode the acoustic data, and using a conversational context associated with the text message. The acoustic data is decoded using the identified acoustic model to produce a plurality of hypotheses for the reply utterance.Type: ApplicationFiled: March 25, 2011Publication date: September 27, 2012Applicant: GENERAL MOTORS LLCInventors: Gaurav Talwar, Xufang Zhao
-
Publication number: 20120209609Abstract: A method of automatic speech recognition includes receiving an utterance from a user via a microphone that converts the utterance into a speech signal, pre-processing the speech signal using a processor to extract acoustic data from the received speech signal, and identifying at least one user-specific characteristic in response to the extracted acoustic data. The method also includes determining a user-specific confidence threshold responsive to the at least one user-specific characteristic, and using the user-specific confidence threshold to recognize the utterance received from the user and/or to assess confusability of the utterance with stored vocabulary.Type: ApplicationFiled: February 14, 2011Publication date: August 16, 2012Applicant: GENERAL MOTORS LLCInventors: Xufang Zhao, Gaurav Talwar
-
Publication number: 20120149356Abstract: A method of operating a vehicle telematics unit includes determining the location of a vehicle equipped with a vehicle telematics unit; determining if telematics dialing software operated by the vehicle telematics unit includes a verbal dialing protocol used at the determined vehicle location; if not, identifying one or more verbal dialing protocols used at the determined location of the vehicle; requesting telematics dialing software that includes the one or more identified verbal dialing protocols; receiving the requested telematics dialing software from a central facility; and storing the received telematics dialing software at the vehicle.Type: ApplicationFiled: December 10, 2010Publication date: June 14, 2012Applicant: General Motors LLCInventors: Uma Arun, Rathinavelu Chengalvarayan, Kevin R. Krause, Eray Yasan, Gaurav Talwar, Xufang Zhao, Michael A. Wuergler
-
Publication number: 20110144987Abstract: A method of automated speech recognition in a vehicle. The method includes receiving audio in the vehicle, pre-processing the received audio to generate acoustic feature vectors, decoding the generated acoustic feature vectors to produce at least one speech hypothesis, and post-processing the at least one speech hypothesis using pitch to improve speech recognition accuracy. The speech hypothesis can be accepted as recognized speech during post-processing if pitch is present in the received audio. Alternatively, a pitch count for the received audio can be determined, N-best speech hypotheses can be post-processed by comparing the pitch count to syllable counts associated with the speech hypotheses, and the speech hypothesis having a syllable count equal to the pitch count can be accepted as recognized speech.Type: ApplicationFiled: December 10, 2009Publication date: June 16, 2011Applicant: GENERAL MOTORS LLCInventors: Xufang Zhao, Uma Arun