Eugene Joshua Weinstein

US Patent:

8494853, Jul 23, 2013

Filed:

Jan 4, 2013

Appl. No.:

13/734296

Inventors:

Pedro J. Moreno Mengibar - Jersey City NJ, US
Eugene Weinstein - New York NY, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 15/26

US Classification:

704235, 7042701, 704270, 704233, 704257

Abstract:

Examples of methods and systems for providing speech recognition systems based on speech recordings logs are described. In some examples, a method may be performed by a computing device within a system to generate modified data logs to use as a training data set for an acoustic model for a particular language. A device may receive one or more data logs that comprise at least one or more recordings of spoken queries and transcribe the recordings. Based on comparisons, the device may identify any transcriptions that may be indicative of noise and may remove those transcriptions indicative of noise from the data logs. Further, the device may remove unwanted transcriptions from the data logs and the device may provide the modified data logs as a training data set to one or more acoustic models for particular languages.

US Patent:

8589164, Nov 19, 2013

Filed:

Mar 15, 2013

Appl. No.:

13/832136

Inventors:

Jeffrey Scott Sorensen - New York NY, US
Eugene Weinstein - New York NY, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 15/14
G10L 15/06
G06F 17/21

US Classification:

704257, 704 10, 704244

Abstract:

Methods and systems for speech recognition processing are described. In an example, a computing device may be configured to receive information indicative of a frequency of submission of a search query to a search engine for a search query composed of a sequence of words. Based on the frequency of submission of the search query exceeding a threshold, the computing device may be configured to determine groupings of one or more words of the search query based on an order in which the one or more words occur in the sequence of words of the search query. Further, the computing device may be configured to provide information indicating the groupings to a speech recognition system.

US Patent:

20120278061, Nov 1, 2012

Filed:

Jul 10, 2012

Appl. No.:

13/545360

Inventors:

Eugene Weinstein - New York NY, US
Pedro J. Moreno Mengibar - New York NY, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G06F 17/28

US Classification:

704 2

Abstract:

This document describes methods, systems, techniques, and computer program products for generating and/or modifying acoustic models. Acoustic models and/or transformations for a target language/dialect can be generated and/or modified using acoustic models and/or transformations from a source language/dialect.

US Patent:

20130297310, Nov 7, 2013

Filed:

Nov 8, 2011

Appl. No.:

13/883964

Inventors:

Eugene Weinstein - New York NY, US
Pedro J. Moreno Mangibar - Jersey City NJ, US

International Classification:

G10L 15/06

US Classification:

704243

Abstract:

This document describes methods, systems, techniques, and computer program products for generating and/or modifying acoustic models. Acoustic models and/or transformations for a target language/dialect can be generated and/or modified using acoustic models and/or transformations from a source language/dialect.

US Patent:

20160267903, Sep 15, 2016

Filed:

May 25, 2016

Appl. No.:

15/164263

Inventors:

- Mountain View CA, US
John Paul Alex - Brooklyn NY, US
Eugene Weinstein - New York NY, US
Pedro J. Moreno Mengibar - Jersey City NJ, US
Olivier Siohan - New York NY, US
Ignacio Lopez Moreno - New York NY, US

International Classification:

G10L 15/06
G10L 15/01
G10L 15/16
G10L 15/30

Abstract:

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. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

US Patent:

20160093294, Mar 31, 2016

Filed:

Apr 22, 2015

Appl. No.:

14/693268

Inventors:

- Mountain View CA, US
John Paul Alex - Brooklyn NY, US
Eugene Weinstein - New York NY, US
Pedro J. Moreno Mengibar - Jersey City NJ, US
Olivier Siohan - New York NY, US
Ignacio Lopez Moreno - New York NY, US

International Classification:

G10L 15/06
G10L 15/187
G10L 15/26
G10L 25/30

Abstract:

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. An updated production speech recognizer component is provided to the production speech recognizer for use in transcribing subsequently received speech data items.

US Patent:

20140114661, Apr 24, 2014

Filed:

Sep 24, 2013

Appl. No.:

14/035083

Inventors:

- Mountain View CA, US
Jeffrey Scott Sorensen - New York NY, US
Eugene Weinstein - New York NY, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 15/06

US Classification:

704244

Abstract:

Methods and systems for speech recognition processing are described. In an example, a computing device may be configured to receive information indicative of a frequency of submission of a search query to a search engine for a search query composed of a sequence of words. Based on the frequency of submission of the search query exceeding a threshold, the computing device may be configured to determine groupings of one or more words of the search query based on an order in which the one or more words occur in the sequence of words of the search query. Further, the computing device may be configured to provide information indicating the groupings to a speech recognition system.