Towards acoustically robust localization of speakers in a reverberant environment

Boaz Rafaely, Dorothea Kolossa, Yanir Maymon

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

8 Scopus citations

Abstract

Direction-of-arrival (DoA) estimation of a speaker in a room using microphone arrays is an important task in audio signal processing in general, and robot audition in particular. Recently, a novel DoA estimation method developed for spherical arrays presented accurate performance even under real-world conditions with strong reverberation. The method identifies time-frequency bins dominated by the direct signal from the source, and employs only these bins for DoA estimation. A recent extension allowed the use of shorter time frames by employing Gaussian mixture model based clustering to the DoA statistics. However, performance still degrades under challenging acoustical conditions, such as close to a reflecting surface. In this paper, a novel analysis is presented that provides insight into the acoustic significance of the individual Gaussians in the mixture, clearly showing the distinctiveness of the Gaussian corresponding to the direct path signal. The results presented here can be employed in the design of acoustically robust DoA estimation under strong reverberation.

Original languageEnglish
Title of host publication2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages96-100
Number of pages5
ISBN (Electronic)9781509059256
DOIs
StatePublished - 10 Apr 2017
Event2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - San Francisco, United States
Duration: 1 Mar 20173 Mar 2017

Publication series

Name2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017 - Proceedings

Conference

Conference2017 Hands-Free Speech Communications and Microphone Arrays, HSCMA 2017
Country/TerritoryUnited States
CitySan Francisco
Period1/03/173/03/17

Keywords

  • Gaussian mixture modeling
  • Reverberation
  • Room acoustics
  • Speaker localization
  • Spherical microphone arrays

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Acoustics and Ultrasonics
  • Instrumentation
  • Communication

Fingerprint

Dive into the research topics of 'Towards acoustically robust localization of speakers in a reverberant environment'. Together they form a unique fingerprint.

Cite this