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:
Mar. 17, 2026

Filed:

Jun. 29, 2023
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Christopher Li, New York, NY (US);

Kyle Scott Kastner, Waltham, MA (US);

Yuan Wang, Hoboken, NJ (US);

Zhehuai Chen, Edgewater, NJ (US);

Andrew Maxwell Rosenberg, Brooklyn, NY (US);

Heng Su, Beijing, CN;

Qian Chen, Beijing, CN;

Leonid Aleksandrovich Velikovich, New York, NY (US);

Patrick Maxim Rondon, New York, NY (US);

Diamantino Antonio Caseiro, Philadelphia, PA (US);

Zelin Wu, Jersey City, NJ (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G10L 25/30 (2013.01); G10L 15/26 (2006.01);
U.S. Cl.
CPC ...
G10L 25/30 (2013.01); G10L 15/26 (2013.01);
Abstract

A method includes receiving training data that includes a set of transcribed speech utterances where each respective transcribed speech utterance is paired with a corresponding transcription. For each respective transcribed speech utterance, the method includes generating an encoded audio representation and an encoded textual representation, generating a higher order audio feature representation for a corresponding encoded audio representation, generating a higher order textual feature representation for a corresponding encoded textual representation, and determining a loss for the respective transcribed speech utterance based on the higher order audio feature representation and the higher order textual feature representation. The method also includes training a speech encoder and a text encoder of a correction model based on the loss determined for each transcribed speech utterance of the set of transcribed speech utterances.


Find Patent Forward Citations

Loading…