The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 17, 2022

Filed:

Aug. 31, 2020
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Fadi Biadsy, Sandyston, NJ (US);

Liyang Jiang, Mountain View, CA (US);

Pedro J. Moreno Mengibar, Jersey City, NJ (US);

Andrew Rosenberg, Mountain View, CA (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G10L 15/06 (2013.01); G10L 15/16 (2006.01); G10L 13/04 (2013.01); G10L 13/047 (2013.01); G10L 15/22 (2006.01); G10L 13/08 (2013.01);
U.S. Cl.
CPC ...
G10L 13/047 (2013.01); G10L 13/08 (2013.01); G10L 15/16 (2013.01); G10L 15/22 (2013.01);
Abstract

A method for training a speech conversion model personalized for a target speaker with atypical speech includes obtaining a plurality of transcriptions in a set of spoken training utterances and obtaining a plurality of unspoken training text utterances. Each spoken training utterance is spoken by a target speaker associated with atypical speech and includes a corresponding transcription paired with a corresponding non-synthetic speech representation. The method also includes adapting, using the set of spoken training utterances, a text-to-speech (TTS) model to synthesize speech in a voice of the target speaker and that captures the atypical speech. For each unspoken training text utterance, the method also includes generating, as output from the adapted TTS model, a synthetic speech representation that includes the voice of the target speaker and that captures the atypical speech. The method also includes training the speech conversion model based on the synthetic speech representations.


Find Patent Forward Citations

Loading…