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:
Jul. 09, 2019

Filed:

Mar. 23, 2018
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Zhong Meng, Redmond, WA (US);

Vadim Aleksandrovich Mazalov, Issaquah, WA (US);

Yifan Gong, Sammamish, WA (US);

Yong Zhao, Redmond, WA (US);

Zhuo Chen, Redmond, WA (US);

Jinyu Li, Redmond, WA (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 25/30 (2013.01); G10L 15/02 (2006.01); G10L 15/16 (2006.01); G10L 15/06 (2013.01);
U.S. Cl.
CPC ...
G10L 15/16 (2013.01); G10L 15/063 (2013.01);
Abstract

Systems and methods can be implemented to conduct speaker-invariant training for speech recognition in a variety of applications. An adversarial multi-task learning scheme for speaker-invariant training can be implemented, aiming at actively curtailing the inter-talker feature variability, while maximizing its senone discriminability to enhance the performance of a deep neural network (DNN) based automatic speech recognition system. In speaker-invariant training, a DNN acoustic model and a speaker classifier network can be jointly optimized to minimize the senone (triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker invariant and senone-discriminative intermediate feature is learned through this adversarial multi-task learning, which can be applied to an automatic speech recognition system. Additional systems and methods are disclosed.


Find Patent Forward Citations

Loading…