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).
-
Patent number: 10319371Abstract: A system and method of recognizing speech in a vehicle. The method includes receiving a voice command at the vehicle via a microphone in the vehicle, and obtaining a recognition result from speech recognition performed on the received voice command. The recognition result may represent the voice command and be indicative of any of two or more available vehicle commands. The method may further include selecting one of the two or more available vehicle commands based on a secondary characteristic and an attribute of the selected one of the vehicle commands. The system may be implemented as vehicle electronics that include a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle, and a controller in communication with the microphone. The controller may be configured to perform speech recognition on the voice command and obtain a disambiguated recognition result.Type: GrantFiled: May 4, 2016Date of Patent: June 11, 2019Assignee: GM Global Technology Operations LLCInventors: Xufang Zhao, Gaurav Talwar
-
Patent number: 10255913Abstract: A system and method of processing disfluent speech at an automatic speech recognition (ASR) system includes: receiving speech from a speaker via a microphone; determining the received speech includes disfluent speech; accessing a disfluent speech grammar or acoustic model in response to the determination; and processing the received speech using the disfluent speech grammar.Type: GrantFiled: February 17, 2016Date of Patent: April 9, 2019Assignee: GM Global Technology Operations LLCInventors: Xufang Zhao, Gaurav Talwar
-
Patent number: 10061554Abstract: A system and method of adjusting digital audio sampling used with wideband audio includes: performing audio sampling on an analog audio signal at an initial sampling rate and an initial bit rate over a wideband audio frequency range; generating a digital audio signal based on the audio sampling; detecting a qualitative error rate between the analog audio signal and the digital audio signal; and decreasing the initial sampling rate, the initial bit rate, or both for sampling subsequent analog audio when the qualitative error is below a threshold.Type: GrantFiled: March 10, 2015Date of Patent: August 28, 2018Assignee: GM Global Technology Operations LLCInventors: Gaurav Talwar, Xufang Zhao, Md Foezur Rahman Chowdhury, Eli Tzirkel-Hancock
-
Patent number: 10008205Abstract: A method of choosing a nametag using automatic speech recognition (ASR) 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: GrantFiled: November 20, 2013Date of Patent: June 26, 2018Assignee: General Motors LLCInventors: Xufang Zhao, Gaurav Talwar, Dipankar Pal, John L. Holdren
-
Patent number: 10006777Abstract: A system and method of recognizing speech received at a vehicle includes: receiving speech from a vehicle occupant via a microphone; determining whether the speech relates to a point of interest (POI) or an address without receiving a POI command prompt or an address command prompt in the speech from the vehicle occupant; selecting a POI function or an address function based on the determination; and processing the received speech to identify a POI or an address.Type: GrantFiled: October 2, 2015Date of Patent: June 26, 2018Assignee: GM Global Technology Operations LLCInventors: Gaurav Talwar, Xufang Zhao
-
Patent number: 10008201Abstract: A system and method of performing automatic speech recognition (ASR) includes: receiving speech at a vehicle microphone; communicating the received speech to an ASR system; measuring an amount of time that elapses while speech is received; selecting a point-of-interest (POI) context or an address context based on the measured amount of received time; and processing the received speech using a POI context-based grammar when a POI context is selected or an address-based grammar when an address context is selected.Type: GrantFiled: September 28, 2015Date of Patent: June 26, 2018Assignee: GM Global Technology Operations LLCInventors: Gaurav Talwar, Ron M. Hecht, Xufang Zhao
-
Patent number: 9911408Abstract: 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: GrantFiled: March 3, 2014Date of Patent: March 6, 2018Assignee: General Motors LLCInventors: John L. Holdren, Gaurav Talwar, Xufang Zhao
-
Patent number: 9881609Abstract: 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: GrantFiled: April 18, 2014Date of Patent: January 30, 2018Assignee: General Motors LLCInventors: Gaurav Talwar, Xufang Zhao
-
Patent number: 9830925Abstract: An automatic speech recognition engine and a method of using the engine is described. The method pertains to front-end processing an audio signal and includes the steps of: identifying a plurality of voiced-frames of the audio signal; determining that one or more of the plurality of voiced-frames have a signal-to-noise (SNR) value greater than a first predetermined threshold; and based on the determination, bypassing noise suppression for the one or more of the plurality of voiced-frames.Type: GrantFiled: October 22, 2014Date of Patent: November 28, 2017Assignee: GM Global Technology Operations LLCInventors: Gaurav Talwar, Xufang Zhao, III, Robert D. Sims, III, Md Foezur Rahman Chowdhury
-
Publication number: 20170323635Abstract: A system and method of recognizing speech in a vehicle. The method includes receiving a voice command at the vehicle via a microphone in the vehicle, and obtaining a recognition result from speech recognition performed on the received voice command. The recognition result may represent the voice command and be indicative of any of two or more available vehicle commands. The method may further include selecting one of the two or more available vehicle commands based on a secondary characteristic and an attribute of the selected one of the vehicle commands. The system may be implemented as vehicle electronics that include a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle, and a controller in communication with the microphone. The controller may be configured to perform speech recognition on the voice command and obtain a disambiguated recognition result.Type: ApplicationFiled: May 4, 2016Publication date: November 9, 2017Inventors: Xufang ZHAO, Gaurav TALWAR
-
Publication number: 20170236511Abstract: A system and method of processing disfluent speech at an automatic speech recognition (ASR) system includes: receiving speech from a speaker via a microphone; determining the received speech includes disfluent speech; accessing a disfluent speech grammar or acoustic model in response to the determination; and processing the received speech using the disfluent speech grammar.Type: ApplicationFiled: February 17, 2016Publication date: August 17, 2017Inventors: Xufang ZHAO, Gaurav TALWAR
-
Patent number: 9704477Abstract: A method is disclosed that provides text-to-speech (TTS) functionality to a telematics unit of a telematics-equipped vehicle. The method includes: receiving text content to be played back by an audio system of the telematics-equipped vehicle; determining, by a processor, a TTS rendering process to be used for the text content from a plurality of TTS rendering processes, wherein the plurality of TTS rendering processes include local TTS rendering using a local TTS engine at the telematics-equipped vehicle and remote TTS rendering using a remote TTS engine at a communications center; and causing, by the processor, the text content to be rendered as an audio signal for playback by the telematics-equipped vehicle using the determined TTS rendering process.Type: GrantFiled: September 5, 2014Date of Patent: July 11, 2017Assignee: GENERAL MOTORS LLCInventors: Xufang Zhao, Omer Tsimhoni, Gaurav Talwar
-
Patent number: 9706299Abstract: 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: GrantFiled: March 13, 2014Date of Patent: July 11, 2017Assignee: GM Global Technology Operations LLCInventors: Gaurav Talwar, MD Foezur Rahman Chowdhury, Xufang Zhao
-
Publication number: 20170097242Abstract: A system and method of recognizing speech received at a vehicle includes: receiving speech from a vehicle occupant via a microphone; determining whether the speech relates to a point of interest (POI) or an address without receiving a POI command prompt or an address command prompt in the speech from the vehicle occupant; selecting a POI function or an address function based on the determination; and processing the received speech to identify a POI or an address.Type: ApplicationFiled: October 2, 2015Publication date: April 6, 2017Inventors: Gaurav TALWAR, Xufang ZHAO
-
Publication number: 20170092295Abstract: A system and method of performing automatic speech recognition (ASR) includes: receiving speech at a vehicle microphone; communicating the received speech to an ASR system; measuring an amount of time that elapses while speech is received; selecting a point-of-interest (POI) context or an address context based on the measured amount of received time; and processing the received speech using a POI context-based grammar when a POI context is selected or an address-based grammar when an address context is selected.Type: ApplicationFiled: September 28, 2015Publication date: March 30, 2017Inventors: Gaurav TALWAR, Ron M. HECHT, Xufang ZHAO
-
Patent number: 9609408Abstract: A hands-free audio system for a vehicle and method of using the system is described. The method includes controlling the directionality of a vehicle microphone. The steps of the method may include: (a) receiving a sensor value from at least one of a vehicle seat position sensor, a vehicle seat orientation sensor, or a vehicle mirror orientation sensor; (b) based on the received sensor value(s) of step (a), determining an origin of a vehicle user's speech; and (c) controlling the microphone sensitivity directionality based on the determined origin.Type: GrantFiled: June 3, 2014Date of Patent: March 28, 2017Assignee: GM Global Technology Operations LLCInventors: Xufang Zhao, Robert D. Sims, III, Md Foezur Rahman Chowdhury, John J. Correia
-
Patent number: 9570066Abstract: 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: GrantFiled: July 16, 2012Date of Patent: February 14, 2017Assignee: General Motors LLCInventors: Gaurav Talwar, Xufang Zhao, Ron M. Hecht
-
Publication number: 20170018273Abstract: A system and method of controlling an automatic speech recognition (ASR) system includes: detecting changes in ambient noise via a microphone in a vehicle equipped with the ASR system; determining an environmental noise compensation value and a channel bias compensation value based on the detected changes; and applying the environmental noise compensation value and a channel bias compensation value to speech received by the ASR system.Type: ApplicationFiled: July 16, 2015Publication date: January 19, 2017Inventors: MD Foezur Rahman CHOWDHURY, Gaurav TALWAR, Xufang ZHAO
-
Patent number: 9530414Abstract: A system and method of controlling an automatic speech recognition (ASR) system includes: receiving speech at the ASR system from a vehicle occupant that includes a command to control a vehicle function; identifying a gate command from the speech; associating the identified gate command with the command to control the vehicle function; storing the associated gate command and vehicle command in a database; receiving additional speech at the ASR system from the vehicle occupant; detecting the gate command in the additional speech; and accessing the stored gate command and vehicle command from the database.Type: GrantFiled: April 14, 2015Date of Patent: December 27, 2016Assignee: GM Global Technology Operations LLCInventors: Xufang Zhao, Gaurav Talwar
-
Publication number: 20160343180Abstract: Automobiles, automobile diagnostic systems, and methods for generating diagnostic data for automobiles are provided. A method for generating diagnostic data for an automobile includes capturing with a sound sensor an acoustic waveform produced by an automobile component. The method converts the acoustic waveform into an electrical waveform data signal. The method includes identifying a pattern in the electrical waveform data signal. Further, the method classifies the pattern as indicative of a selected performance issue.Type: ApplicationFiled: May 19, 2015Publication date: November 24, 2016Inventors: GAURAV TALWAR, XUFANG ZHAO, MD FOEZUR RAHMAN CHOWDHURY