David F Schulz

US Patent:

20070255567, Nov 1, 2007

Filed:

Apr 27, 2006

Appl. No.:

11/380496

Inventors:

Srinivas Bangalore - Morristown NJ, US
David Schulz - Wauwatosa WI, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G10L 13/08
G10L 13/00

US Classification:

704260000

Abstract:

Disclosed is a system, method and computer-readable medium that stores instructions for controlling a computing device. The method embodiment relates to processing speech data wherein the method comprises generating phoneme transcriptions for words in a first language, generating a pronunciation dictionary comprising three-parts including, for each word in the dictionary, a first part having a first language orthography, a second part having a second language pronunciation and a third part having a second language orthography and applying the pronunciation dictionary in a speech application. The method is especially applicable to languages where the alphabet does not fully represent how a word is pronounced, as in Arabic or Hebrew.

US Patent:

54757339, Dec 12, 1995

Filed:

Sep 1, 1994

Appl. No.:

8/299937

Inventors:

Jerry Eisdorfer - Somerset NJ
Leonard R. Kasday - Moorestown NJ
David E. Schulz - Wheaton IL

Assignee:

AT&T Corp. - Murray Hill NJ

International Classification:

H04M 1100

US Classification:

379 52

Abstract:

A call between a caller using a telephone device for the deaf (TDD) using a one of a number of languages and another including a TDD user is connected by automatically prompting the TDD caller for calling information, automatically identifying the language being used, parsing the received calling information in the appropriate language to determine a forward number, selecting a communication assistant (CA) capable of speaking in the language routing the call to the selected CA, and connecting the call. One embodiment involves storing the forward number before routing the call so the selected CA can press a single button to connect the call. According to an embodiment of the invention, the calling information is passed directly to a number of language specific parsers and the successful parser determines the language being used.

US Patent:

57455503, Apr 28, 1998

Filed:

Jun 7, 1995

Appl. No.:

8/476811

Inventors:

Jerry Eisdorfer - Somerset NJ
Leonard R. Kasday - Moorestown NJ
David E. Schulz - Wheaton IL

Assignee:

AT&T - Middletown NJ

International Classification:

H04M 1100

US Classification:

379 52

Abstract:

A call between a caller using a telephone device for the deaf (TDD), and requiring one or more types of expertise from a calling assistant, and another person, including a TDD user, is connected by automatically prompting the TDD caller for calling information, automatically identifying the expertise needed, including the language being used, selecting a communication assistant (CA) capable of speaking in the language and other expertise, routing the call to the selected CA, and connecting the call.

US Patent:

20170330554, Nov 16, 2017

Filed:

Jul 31, 2017

Appl. No.:

15/664694

Inventors:

- Burlington MA, US
Junlan FENG - North Plainfield NJ, US
Mazin GILBERT - Warren NJ, US
Juergen SCHROETER - New Providence NJ, US
Ann K. SYRDAL - San Jose CA, US
David SCHULZ - Wauwatosa WI, US

International Classification:

G10L 13/033
G10L 13/02
G10L 15/197
G10L 13/06
G10L 13/08
G10L 13/00

Abstract:

A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

US Patent:

20160093287, Mar 31, 2016

Filed:

Dec 10, 2015

Appl. No.:

14/965251

Inventors:

- Atlanta GA, US
Junlan FENG - North Plainfield NJ, US
Mazin GILBERT - Warren NJ, US
Juergen SCHROETER - New Providence NJ, US
Ann K. SYRDAL - San Jose CA, US
David SCHULZ - Wauwatosa WI, US

International Classification:

G10L 13/033
G10L 15/197

Abstract:

A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

US Patent:

20140188480, Jul 3, 2014

Filed:

Mar 4, 2014

Appl. No.:

14/196578

Inventors:

- Atlanta GA, US
Junlan Feng - North Plainfield NJ, US
Mazin G. Rahim - Warren NJ, US
Juergen Schroeter - New Providence NJ, US
Ann K. Syrdal - Morristown NJ, US
David Schulz - Wauwatosa WI, US

Assignee:

AT&T Intellectual Property II, L.P. - Atlanta GA

International Classification:

G10L 13/02

US Classification:

704260

Abstract:

A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.

US Patent:

20050256716, Nov 17, 2005

Filed:

May 13, 2004

Appl. No.:

10/845364

Inventors:

Srinivas Bangalore - Morristown NJ, US
Junlan Feng - North Plainfield NJ, US
Mazin Rahim - Warren NJ, US
Juergen Schroeter - New Providence NJ, US
David Schulz - St. Peter MN, US
Ann Syrdal - Morristown NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G10L013/00

US Classification:

704260000

Abstract:

A system and method are disclosed for generating customized text-to-speech voices for a particular application. The method comprises generating a custom text-to-speech voice by selecting a voice for generating a custom text-to-speech voice associated with a domain, collecting text data associated with the domain from a pre-existing text data source and using the collected text data, generating an in-domain inventory of synthesis speech units by selecting speech units appropriate to the domain via a search of a pre-existing inventory of synthesis speech units, or by recording the minimal inventory for a selected level of synthesis quality. The text-to-speech custom voice for the domain is generated utilizing the in-domain inventory of synthesis speech units. Active learning techniques may also be employed to identify problem phrases wherein only a few minutes of recorded data is necessary to deliver a high quality TTS custom voice.