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:
Aug. 13, 2019

Filed:

Apr. 27, 2017
Applicant:

Motorola Solutions, Inc, Chicago, IL (US);

Inventors:

Cheah Heng Tan, Bayan Lepas, MY;

Thean Hai Ooi, Batu Maung, MY;

Wei Qing Ong, Segamat, MY;

Alan Wee Chiat Tan, Taman Jati, MY;

Assignee:

MOTOROLA SOLUTIONS, INC., Chicago, IL (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 25/84 (2013.01); G10L 25/18 (2013.01); G10L 25/78 (2013.01); G10L 25/03 (2013.01);
U.S. Cl.
CPC ...
G10L 25/84 (2013.01); G10L 25/03 (2013.01); G10L 25/18 (2013.01); G10L 2025/786 (2013.01);
Abstract

A voice activity detection system () filters audio input frames (), on a frame=by-frame basis through a gammatone filterbank () to generate filtered gammatone output signals (). A signal energy calculator () takes the filtered gammatone output signals and generates a plurality of energy envelopes. Weighting factors are constructed () are applied to each of the energy envelopes thereby producing normalized weighted signal (), in which voice regions are emphasized and noise regions are minimized. An entropy measurement () is taken to extract information from the normalized weighted signals () and generate an entropy signal (). The entropy signal () is averaged and compared to an adaptive entropy threshold (), indicative of a noise floor. Decision logic () is used to identifying speech and noise from the comparison of the averaged entropy signal to the adaptive entropy threshold.


Find Patent Forward Citations

Loading…