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:
Oct. 24, 2023

Filed:

Jan. 29, 2021
Applicant:

Salesforce.com, Inc., San Francisco, CA (US);

Inventors:

Guangsen Wang, Singapore, SG;

Chu Hong Hoi, Singapore, SG;

Genta Indra Winata, Singapore, SG;

Assignee:

salesforce.com, inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G10L 15/16 (2006.01); G10L 15/065 (2013.01); G06N 3/08 (2023.01); G06N 3/04 (2023.01); G10L 15/06 (2013.01);
U.S. Cl.
CPC ...
G10L 15/16 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G10L 15/063 (2013.01); G10L 15/065 (2013.01);
Abstract

Embodiments described herein provide an Adapt-and-Adjust (A2) mechanism for multilingual speech recognition model that combines both adaptation and adjustment methods as an integrated end-to-end training to improve the models' generalization and mitigate the long-tailed issue. Specifically, a multilingual language model mBERT is utilized, and converted into an autoregressive transformer decoder. In addition, a cross-attention module is added to the encoder on top of the mBERT's self-attention layer in order to explore the acoustic space in addition to the text space. The joint training of the encoder and mBERT decoder can bridge the semantic gap between the speech and the text.


Find Patent Forward Citations

Loading…