Multi-microphone voice activity and single-Talk detectors based on steered-response power output entropy

Ofer Schwartz, Aviv David, Ofer Shahen-Tov, Sharon Gannot

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Voice activity detection (VAD), namely determining whether a speech signal is active or inactive, and single talk detector (STD), namely detecting that only one speaker is active, are important building blocks in many speech processing applications. A speaker-localization stage (such as the steered response power (SRP)) is often concurrently implemented on the same device.In this paper, the spatial properties of the SRP are utilized for improving the performance of both the voice activity detector (VAD) and the STD. We propose to measure the entropy at the SRP output and compare with the typical entropy of noise-only frames. This feature utilizes spatial information and may therefore become advantageous in nonstationary noise environments. The STD can then be implemented by determining local minimum values of the entropy measure of the SRP.The proposed VAD was tested for a single speaker with two cases, directional background noise with changing level and with a background music source. The proposed STD was tested using real recordings of two concurrent speakers.

Original languageEnglish
Title of host publication2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538663783
DOIs
StatePublished - 2 Jul 2018
Event2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018 - Eilat, Israel
Duration: 12 Dec 201814 Dec 2018

Publication series

Name2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018

Conference

Conference2018 IEEE International Conference on the Science of Electrical Engineering in Israel, ICSEE 2018
Country/TerritoryIsrael
CityEilat
Period12/12/1814/12/18

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Multi-microphone voice activity and single-Talk detectors based on steered-response power output entropy'. Together they form a unique fingerprint.

Cite this