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. 27, 2025

Filed:

Dec. 14, 2022
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Soheil Khorram, Redwood City, CA (US);

Anshuman Tripathi, Mountain View, CA (US);

Kim Jaeyoung, Cupertino, CA (US);

Han Lu, Redmond, WA (US);

Qian Zhang, Mountain View, CA (US);

Hasim Sak, Santa Clara, CA (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G10L 15/00 (2013.01); G10L 15/06 (2013.01); G10L 15/183 (2013.01); G10L 15/22 (2006.01); G10L 15/02 (2006.01);
U.S. Cl.
CPC ...
G10L 15/183 (2013.01); G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 15/02 (2013.01);
Abstract

A method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. The method also includes generating, using a supervised audio encoder, a target higher order feature representation for a corresponding acoustic frame. The method also includes augmenting the sequence of acoustic frames and generating, as output form an unsupervised audio encoder, a predicted higher order feature representation for a corresponding augmented acoustic frame in the sequence of augmented acoustic frames. The method also includes determining an unsupervised loss term based on the target higher order feature representation and the predicted higher order feature representation and updating parameters of the speech recognition model based on the unsupervised loss term.


Find Patent Forward Citations

Loading…