Wei Te Chai

US Patent:

20070118364, May 24, 2007

Filed:

Oct 25, 2006

Appl. No.:

11/552530

Inventors:

Gerald Wise - Clifton Park NY, US
Louis Hoebel - Burnt Hills NY, US
John Lizzi - Wilton NY, US
Wei Chai - Niskayuna NY, US
Helena Goldfarb - Niskayuna NY, US
Anil Abraham - New York NY, US
Richard Zinser - Niskayuna NY, US

International Classification:

G10L 11/06

US Classification:

704215000, 704260000

Abstract:

A system for detecting and modifying breath pauses in a speech input signal includes a breath detection unit connected to receive the speech input signal and to detect breath pauses. The system also includes a modification unit connected to receive input from the breath detection unit and to replace the breath pauses with a predetermined input and/or to attenuate the breath pauses. The breath detection unit is further configured to output an output speech signal.

US Patent:

20070118372, May 24, 2007

Filed:

Nov 23, 2005

Appl. No.:

11/287556

Inventors:

Gerald Wise - Clifton Park NY, US
Louis Hoebel - Burnt Hills NY, US
John Lizzi - Albany NY, US
Wei Chai - Niskayuna NY, US
Helena Goldfarb - Niskayuna NY, US
Anil Abraham - Latham NY, US

International Classification:

G10L 15/26

US Classification:

704235000

Abstract:

A system for generating closed captions is provided. The system includes a speech recognition engine configured to generate one or more text transcripts corresponding to one or more speech segments from an audio signal. The system further includes a processing engine, one or more context-based models and an encoder. The processing engine is configured to process the text transcripts. The context-based models are configured to identify an appropriate context associated with the text transcripts. The encoder is configured to broadcast the text transcripts corresponding to the speech segments as closed captions.

US Patent:

20070118373, May 24, 2007

Filed:

Oct 5, 2006

Appl. No.:

11/538936

Inventors:

Gerald Wise - Clifton Park NY, US
Louis Hoebel - Burnt Hills NY, US
John Lizzi - Wilton NY, US
Wei Chai - Niskayuna NY, US
Helena Goldfarb - Niskayuna NY, US
Anil Abraham - New York NY, US
Richard Zinser - Niskayuna NY, US

International Classification:

G10L 15/26

US Classification:

704235000

Abstract:

A system for generating closed captions from an audio signal includes an audio pre-processor configured to correct one or more predetermined undesirable attributes from an audio signal and to output one or more speech segments. The system also includes a speech recognition module configured to generate from the one or more speech segments one or more text transcripts and a post processor configured to provide at least one pre-selected modification to the text transcripts. Further included is an encoder configured to broadcast modified text transcripts corresponding to the speech segments as closed captions.

US Patent:

20070118374, May 24, 2007

Filed:

Oct 25, 2006

Appl. No.:

11/552533

Inventors:

Gerald Wise - Clifton Park NY, US
Louis Hoebel - Burnt Hills NY, US
John Lizzi - Wilton NY, US
Wei Chai - Niskayuna NY, US
Helena Goldfarb - Niskayuna NY, US
Anil Abraham - New York NY, US
Richard Zinser - Niskayuna NY, US

International Classification:

G10L 15/26

US Classification:

704235000, 704233000

Abstract:

A method for detecting and modifying breath pauses in a speech input signal includes detecting breath pauses in a speech input signal; modifying the breath pauses by replacing the breath pauses with a predetermined input and/or attenuating the breath pauses; and outputting an output speech signal. A computer program for carrying out the method is also presented.

US Patent:

20110218883, Sep 8, 2011

Filed:

Mar 3, 2010

Appl. No.:

12/717088

Inventors:

Daniel-Alexander Billsus - San Francisco CA, US
Wei Chai - Union City CA, US
Sam P. Hamilton - Los Altos CA, US
Jonathan Blake Handler - Redwood City CA, US
Nir Yeffet - Cupertino CA, US

International Classification:

G06F 17/30
G06Q 30/00

US Classification:

705 271, 707771, 707E17014, 705 2625

Abstract:

The browsing activity of a first user is motivated by some intent. The first user requests retrieval of a particular document while browsing. A document processing and presentation machine associates the document with a retrieval path taken by the first user. By using the retrieval path data of the document, the document processing and presentation machine infers an intent that likely motivated the first user. When a second user makes a request similar to a request within the retrieval path, the machine presents the second user with the document and some of the retrieval path data, thus providing the second user with a shortcut that leads the second user directly to the document. Thus, the second user may be able to satisfy his intent with significantly less browsing activity compared to the first user.

US Patent:

20110219029, Sep 8, 2011

Filed:

Mar 3, 2010

Appl. No.:

12/717082

Inventors:

Daniel-Alexander Billsus - San Francisco CA, US
Wei Chai - Union City CA, US
Sam P. Hamilton - Los Altos CA, US
Jonathan Blake Handler - Redwood City CA, US
Nir Yeffet - Cupertino CA, US

International Classification:

G06F 17/30
G06F 15/16
G06Q 30/00

US Classification:

707770, 709203, 707E17107, 705 271, 705 261

Abstract:

The browsing activity of a first user is motivated by some intent. The first user requests retrieval of a particular document while browsing. A document processing and presentation machine associates the document with a retrieval path taken by the first user. By using the retrieval path data of the document, the document processing and presentation machine infers an intent that likely motivated the first user. When a second user makes a request similar to a request within the retrieval path, the machine presents the second user with the document and some of the retrieval path data, thus providing the second user with a shortcut that leads the second user directly to the document. Thus, the second user may be able to satisfy his intent with significantly less browsing activity compared to the first user.

US Patent:

20110219030, Sep 8, 2011

Filed:

Mar 3, 2010

Appl. No.:

12/717091

Inventors:

Daniel-Alexander Billsus - San Francisco CA, US
Wei Chai - Union City CA, US
Sam P. Hamilton - Los Altos CA, US
Jonathan Blake Handler - Redwood City CA, US
Nir Yeffet - Cupertino CA, US

International Classification:

G06F 17/30
G06F 15/16
G06F 17/00
G06Q 30/00

US Classification:

707770, 707E17108, 707E17008, 705 271

Abstract:

The browsing activity of a first user is motivated by some intent. The first user requests retrieval of a particular document while browsing. A document processing and presentation machine associates the document with a retrieval path taken by the first user. By using the retrieval path data of the document, the document processing and presentation machine infers an intent that likely motivated the first user. When a second user makes a request similar to a request within the retrieval path, the machine presents the second user with the document and some of the retrieval path data, thus providing the second user with a shortcut that leads the second user directly to the document. Thus, the second user may be able to satisfy his intent with significantly less browsing activity compared to the first user.

US Patent:

20200372359, Nov 26, 2020

Filed:

Aug 12, 2020

Appl. No.:

16/991258

Inventors:

- Mountain View CA, US
Rohan Anil - San Francisco CA, US
Hrishikesh Balkrishna Aradhye - Mountain View CA, US
Mustafa Ispir - Mountain View CA, US
Glen Anderson - Palo Alto CA, US
Wei Chai - Cupertino CA, US
Mehmet Levent Koc - Mountain View CA, US
Jeremiah Joseph Harmsen - Zurich, CH
Xiaobing Liu - Sunnyvale CA, US
Gregory Sean Corrado - San Francisco CA, US
Tushar Deepak Chandra - Los Altos CA, US

International Classification:

G06N 3/08
G06N 3/04

Abstract:

A system includes one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the computers to implement a combined machine learning model for processing an input including multiple features to generate a predicted output for the machine learning input. The combined model includes: a deep machine learning model configured to process the features to generate a deep model output; a wide machine learning model configured to process the features to generate a wide model output; and a combining layer configured to process the deep model output generated by the deep machine learning model and the wide model output generated by the wide machine learning model to generate the predicted output, in which the deep model and the wide model have been trained jointly on training data to generate the deep model output and the wide model output.