David R Schulz

US Patent:

7630898, Dec 8, 2009

Filed:

Sep 27, 2005

Appl. No.:

11/235817

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 13/06
G06F 17/27
G10L 13/08

US Classification:

704266, 704 9, 704260

Abstract:

Disclosed are various elements of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. One embodiment of the invention relates to a method of generating a database for a TTS voice. The method comprises matching every spoken word associated with a TTS voice database with a smallest set of possible pronunciations for each word. The smallest set is generated by automatically determining a dialect and linguistic context using linguistic rules, empirically determining idiosyncratic speaker characteristics and determining a subject domain. The method further comprises dynamically generating a pronunciation dictionary on a word-by-word basis using the smallest set.

US Patent:

7693716, Apr 6, 2010

Filed:

Sep 27, 2005

Appl. No.:

11/235954

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 13/08

US Classification:

704260, 704258, 704267

Abstract:

Disclosed herein are various aspects of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method of tracking progress in developing a text-to-speech (TTS) voice. The method comprises insuring that a corpus of recorded speech contains reading errors and matches an associated written text, creating a tuple for each utterance in the corpus and tracking progress for each utterance utilizing the tuple. Various parameters may be tracked using the tuple but the tuple provides a means for enabling multiple workers to efficiently process a database of utterance in preparation of a TTS voice.

US Patent:

7711562, May 4, 2010

Filed:

Sep 27, 2005

Appl. No.:

11/235822

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 13/00

US Classification:

704258, 704 9

Abstract:

Disclosed are various elements of a toolkit used for generating a TTS voice for use in a spoken dialog system. The invention in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method for preparing a text-to-speech (TTS) voice for testing and verification. The method comprises processing a TTS voice to be ready for testing, synthesizing words utilizing the TTS voice, presenting to a person a smallest possible subset that contains at least N instances of a group of units in the TTS voice, receiving information from the person associated with corrections needed to the TTS voice and making corrections to the TTS voice according to the received information.

US Patent:

7742919, Jun 22, 2010

Filed:

Sep 27, 2005

Appl. No.:

11/235857

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 13/08

US Classification:

704260, 704244, 704258

Abstract:

The present invention provides various elements of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. One embodiment of the invention relates to a method of correcting a database associated with the development of a text-to-speech (TTS) voice. The method comprises generating a pronunciation dictionary for use with a TTS voice, generating a TTS voice to a stage wherein it is prepared to be tested before being deployed, identifying mislabeled phonetic units associated with the TTS voice, for each identified mislabeled phonetic unit, linking to an entry within the pronunciation dictionary to correct the entry and deleting utterances and all associated data for unacceptable utterances.

US Patent:

7742921, Jun 22, 2010

Filed:

Sep 27, 2005

Appl. No.:

11/235821

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 21/00
G10L 15/26
G10L 13/00

US Classification:

704270, 704235, 704258

Abstract:

Disclosed herein are various innovations associated with a toolkit used for generating a TTS voice for use in a spoken dialog system. The inventions in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method of enabling human workers to find errors when developing a text-to-speech (TTS) voice. The method comprises presenting a graphical user interface wherein after a first pass of automatic speech recognition (ASR) of a speech corpus is complete, the interface presents to a worker a graphical representation of an alignment of the ASR results, associated words and phonemes and the audio, receiving a graphical input from the worker associated with a selection of a word or phoneme and presenting the audio associated with the selected word or phoneme.

US Patent:

8073694, Dec 6, 2011

Filed:

Dec 23, 2009

Appl. No.:

12/646125

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

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

International Classification:

G10L 13/00
G06F 17/27

US Classification:

704258, 704 9

Abstract:

Disclosed are various elements of a toolkit used for generating a TTS voice for use in a spoken dialog system. The invention in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method for preparing a text-to-speech (TTS) voice for testing and verification. The method comprises processing a TTS voice to be ready for testing, synthesizing words utilizing the TTS voice, presenting to a person a smallest possible subset that contains at least N instances of a group of units in the TTS voice, receiving information from the person associated with corrections needed to the TTS voice and making corrections to the TTS voice according to the received information.

US Patent:

7996226, Aug 9, 2011

Filed:

Dec 15, 2009

Appl. No.:

12/638648

Inventors:

Steven Lawrence Davis - Madelia MN, US
Shane Fetters - St. Peter MN, US
David Eugene Schulz - Wauwatosa WI, US
Beverly Gustafson - St. Peter MN, US
Louise Loney - Elysian MN, US

Assignee:

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

International Classification:

G10L 13/08

US Classification:

704260, 704266, 704270

Abstract:

Disclosed herein are various aspects of a toolkit used for generating a TTS voice for use in a spoken dialog system. The embodiments in each case may be in the form of the system, a computer-readable medium or a method for generating the TTS voice. An embodiment of the invention relates to a method of tracking progress in developing a text-to-speech (TTS) voice. The method comprises insuring that a corpus of recorded speech contains reading errors and matches an associated written text, creating a tuple for each utterance in the corpus and tracking progress for each utterance utilizing the tuple. Various parameters may be tracked using the tuple but the tuple provides a means for enabling multiple workers to efficiently process a database of utterance in preparation of a TTS voice.