Multi Target Acoustic Source Tracking with an Unknown and Time Varying Number of Targets

M. Fallon, S.J. Godsill

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Particle Filter-based Acoustic Source Tracking algorithms track (online and in real-time) the position of a sound source - a person speaking in a room - based on the current data from a distributed microphone array as well as all previous data up to that point. This paper develops a previously introduced multi-target (MTT) methodology to allow for an unknown and time-varying number of speakers. Finally examples show typical tracking performance in a number of different scenarios with simultaneously active speech sources.
Original languageEnglish
Title of host publicationHands-Free Speech Communication and Microphone Arrays, 2008. HSCMA 2008
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages77-80
Number of pages4
ISBN (Electronic)978-1-4244-2338-5
ISBN (Print)978-1-4244-2337-8
DOIs
Publication statusPublished - 1 May 2008

Keywords

  • acoustic signal processing
  • microphone arrays
  • particle filtering (numerical methods)
  • probability
  • speaker recognition
  • speech processing
  • target tracking
  • distributed microphone array
  • multitarget acoustic source tracking
  • particle filter
  • speaker detection
  • Acoustic signal processing
  • Filtering
  • Laboratories
  • Microphone arrays
  • Particle tracking
  • Proposals
  • Signal processing algorithms
  • Speech enhancement
  • Surveillance
  • Target tracking
  • Acoustic tracking
  • Microphones
  • Monte Carlo methods
  • Speech processing

Fingerprint

Dive into the research topics of 'Multi Target Acoustic Source Tracking with an Unknown and Time Varying Number of Targets'. Together they form a unique fingerprint.

Cite this