Patents by Inventor Eugene Weinstein
Eugene Weinstein 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: 20240161732Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: ApplicationFiled: January 20, 2024Publication date: May 16, 2024Applicant: Google LLCInventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Publication number: 20240078602Abstract: According to one embodiment, a method of generating a display of a limit order book is provided. Data regarding a plurality of limit orders entered onto an electronic market is received and recorded, at least temporarily. The data regarding each limit order includes a price and a time associated with that limit order. Based on the received data, a graphical display is generated that indicates, for each recorded limit order entered into the electronic market within a period of time, the price and the time associated with that limit order. The price associated with each limit order is indicated by a first axis of the graphical display and the time associated with each limit order is indicated by a second axis of the graphical display. The graphical display may be displayed using an electronic display device.Type: ApplicationFiled: April 27, 2023Publication date: March 7, 2024Inventors: Jeffrey M. Bandman, Nathan J. Ondyak, Eugene M. Sorenson, Bernie A. Weinstein
-
Patent number: 11900915Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: GrantFiled: January 10, 2022Date of Patent: February 13, 2024Assignee: Google LLCInventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Patent number: 11620104Abstract: Characteristics of a speaker are estimated using speech processing and machine learning. The characteristics of the speaker are used to automatically customize a user interface of a client device for the speaker.Type: GrantFiled: July 11, 2022Date of Patent: April 4, 2023Assignee: Google LLCInventors: Eugene Weinstein, Ignacio L. Moreno
-
Publication number: 20220342632Abstract: Characteristics of a speaker are estimated using speech processing and machine learning. The characteristics of the speaker are used to automatically customize a user interface of a client device for the speaker.Type: ApplicationFiled: July 11, 2022Publication date: October 27, 2022Applicant: Google LLCInventors: Eugene Weinstein, Ignacio L. Moreno
-
Patent number: 11403065Abstract: Characteristics of a speaker are estimated using speech processing and machine learning. The characteristics of the speaker are used to automatically customize a user interface of a client device for the speaker.Type: GrantFiled: December 29, 2020Date of Patent: August 2, 2022Assignee: Google LLCInventors: Eugene Weinstein, Ignacio L. Moreno
-
Publication number: 20220130374Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: ApplicationFiled: January 10, 2022Publication date: April 28, 2022Applicant: Google LLCInventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Patent number: 11238845Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: GrantFiled: November 14, 2019Date of Patent: February 1, 2022Assignee: Google LLCInventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Patent number: 11137977Abstract: The characteristics of the speaker may be used to automatically customize a user interface of a client device for the speaker. For instance, a mobile device may generate a user interface that does not permit access to particular applications on the mobile device, that only includes options to call home and access a camera application, or that includes an override option to cause generation of a user interface for a different class of user than a user class for the automatic customizations applied to the user interface.Type: GrantFiled: August 8, 2016Date of Patent: October 5, 2021Assignee: Google LLCInventors: Eugene Weinstein, Ignacio L. Moreno
-
Publication number: 20210117153Abstract: Characteristics of a speaker are estimated using speech processing and machine learning. The characteristics of the speaker are used to automatically customize a user interface of a client device for the speaker.Type: ApplicationFiled: December 29, 2020Publication date: April 22, 2021Applicant: Google LLCInventors: Eugene Weinstein, Ignacio L. Moreno
-
Publication number: 20200160836Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.Type: ApplicationFiled: November 14, 2019Publication date: May 21, 2020Inventors: Zhifeng Chen, Bo Li, Eugene Weinstein, Yonghui Wu, Pedro J. Moreno Mengibar, Ron J. Weiss, Khe Chai Sim, Tara N. Sainath, Patrick An Phu Nguyen
-
Patent number: 9990925Abstract: The present disclosure relates to training a speech recognition system. A system that includes an automated speech recognizer and receives data from a client device. The system determines that at least a portion of the received data is likely sensitive data. Before the at least a portion of the received data is deleted, the system provides the at least a portion of the received data to a model training engine that trains recognition models for the automated speech recognizer. After the at least a portion of the received data is provided, the system deletes the at least a portion of the received data.Type: GrantFiled: December 14, 2017Date of Patent: June 5, 2018Assignee: Google LLCInventors: Eugene Weinstein, Pedro J. Moreno Mengibar
-
Publication number: 20180108355Abstract: The present disclosure relates to training a speech recognition system. A system that includes an automated speech recognizer and receives data from a client device. The system determines that at least a portion of the received data is likely sensitive data. Before the at least a portion of the received data is deleted, the system provides the at least a portion of the received data to a model training engine that trains recognition models for the automated speech recognizer. After the at least a portion of the received data is provided, the system deletes the at least a portion of the received data.Type: ApplicationFiled: December 14, 2017Publication date: April 19, 2018Inventors: Eugene Weinstein, Pedro J. Moreno Mengibar
-
Patent number: 9881613Abstract: The present disclosure relates to training a speech recognition system. A system that includes an automated speech recognizer and receives data from a client device. The system determines that at least a portion of the received data is likely sensitive data. Before the at least a portion of the received data is deleted, the system provides the at least a portion of the received data to a model training engine that trains recognition models for the automated speech recognizer. After the at least a portion of the received data is provided, the system deletes the at least a portion of the received data.Type: GrantFiled: June 29, 2015Date of Patent: January 30, 2018Assignee: Google LLCInventors: Eugene Weinstein, Pedro J. Moreno Mengibar
-
Patent number: 9858922Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for caching speech recognition scores. In some implementations, one or more values comprising data about an utterance are received. An index value is determined for the one or more values. An acoustic model score for the one or more received values is selected, from a cache of acoustic model scores that were computed before receiving the one or more values, based on the index value. A transcription for the utterance is determined using the selected acoustic model score.Type: GrantFiled: June 23, 2014Date of Patent: January 2, 2018Assignee: Google Inc.Inventors: Eugene Weinstein, Sanjiv Kumar, Ignacio L. Moreno, Andrew W. Senior, Nikhil Prasad Bhat
-
Publication number: 20160379639Abstract: The present disclosure relates to training a speech recognition system. A system that includes an automated speech recognizer and receives data from a client device. The system determines that at least a portion of the received data is likely sensitive data. Before the at least a portion of the received data is deleted, the system provides the at least a portion of the received data to a model training engine that trains recognition models for the automated speech recognizer. After the at least a portion of the received data is provided, the system deletes the at least a portion of the received data.Type: ApplicationFiled: June 29, 2015Publication date: December 29, 2016Inventors: Eugene Weinstein, Pedro J. Moreno Mengibar
-
Publication number: 20160342389Abstract: Characteristics of a speaker are estimated using speech processing and machine learning. The characteristics of the speaker are used to automatically customize a user interface of a client device for the speaker.Type: ApplicationFiled: August 8, 2016Publication date: November 24, 2016Inventors: Eugene Weinstein, Ignacio L. Moreno
-
Patent number: 9472187Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer.Type: GrantFiled: May 25, 2016Date of Patent: October 18, 2016Assignee: Google Inc.Inventors: Olga Kapralova, John Paul Alex, Eugene Weinstein, Pedro J. Moreno Mengibar, Olivier Siohan, Ignacio Lopez Moreno
-
Publication number: 20160267903Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer.Type: ApplicationFiled: May 25, 2016Publication date: September 15, 2016Inventors: Olga Kapralova, John Paul Alex, Eugene Weinstein, Pedro J. Moreno Mengibar, Olivier Siohan, Ignacio Lopez Moreno
-
Patent number: 9378731Abstract: The present disclosure relates to training a speech recognition system. One example method includes receiving a collection of speech data items, wherein each speech data item corresponds to an utterance that was previously submitted for transcription by a production speech recognizer. The production speech recognizer uses initial production speech recognizer components in generating transcriptions of speech data items. A transcription for each speech data item is generated using an offline speech recognizer, and the offline speech recognizer components are configured to improve speech recognition accuracy in comparison with the initial production speech recognizer components. The updated production speech recognizer components are trained for the production speech recognizer using a selected subset of the transcriptions of the speech data items generated by the offline speech recognizer.Type: GrantFiled: April 22, 2015Date of Patent: June 28, 2016Assignee: Google Inc.Inventors: Olga Kapralova, John Paul Alex, Eugene Weinstein, Pedro J. Moreno Mengibar, Olivier Siohan, Ignacio Lopez Moreno