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:
Jan. 07, 2025

Filed:

Apr. 25, 2022
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Andrew M. Rosenberg, Brooklyn, NY (US);

Gary Wang, Brooklyn, NY (US);

Bhuvana Ramabhadran, Mt. Kisco, NY (US);

Fadi Biadsy, Mountain View, CA (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G10L 15/06 (2013.01); G10L 13/02 (2013.01); G10L 15/197 (2013.01); G10L 15/22 (2006.01); G10L 19/038 (2013.01); G10L 21/003 (2013.01); G10L 15/16 (2006.01); G10L 19/00 (2013.01);
U.S. Cl.
CPC ...
G10L 15/063 (2013.01); G10L 13/02 (2013.01); G10L 15/197 (2013.01); G10L 15/22 (2013.01); G10L 19/038 (2013.01); G10L 21/003 (2013.01); G10L 2015/0635 (2013.01); G10L 15/16 (2013.01); G10L 2019/0001 (2013.01);
Abstract

A method includes receiving a set of training utterances each including a non-synthetic speech representation of a corresponding utterance, and for each training utterance, generating a corresponding synthetic speech representation by using a voice conversion model. The non-synthetic speech representation and the synthetic speech representation form a corresponding training utterance pair. At each of a plurality of output steps for each training utterance pair, the method also includes generating, for output by a speech recognition model, a first probability distribution over possible non-synthetic speech recognition hypotheses for the non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses for the synthetic speech representation. The method also includes determining a consistent loss term for the corresponding training utterance pair based on the first and second probability distributions and updating parameters of the speech recognition model based on the consistent loss term.


Find Patent Forward Citations

Loading…