Multispeaker direction of arrival tracking for multimodal source separation of moving sources

Ata-Ur-Rehman, Syed Mohsen Naqvi, Raphael Phan, Jonathon A. Chambers

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

Abstract

An improvement is proposed in the audio-visual approach to solve the problem of source separation of physically moving speakers by exploiting multiple video cameras, a circular microphone array and robust spatial beamforming. The challenge of separating moving sources is that the mixing filters are time varying; as such the unmixing filters should also be time varying but these are difficult to determine from only audio measurements. Therefore the visual modality is utilized to track the direction of each speaker to the microphone array by using a Markov chain Monte Carlo particle filter (MCMC-PF). The proposed direction of arrival (DOA) tracker improves the computational complexity with respect to a previously employed 3-D multi-speaker position tracker. The DOA information is used in a robust least squares frequency invariant data independent (RLSFIDI) beamformer to separate the audio sources. Experimental results show that the proposed technique efficiently tracks the DOA with improved computational complexity and enhanced source separation.

Original languageEnglish
Title of host publicationSensor Signal Processing for Defence, SSPD 2011
Edition4
DOIs
Publication statusPublished - 2011
Externally publishedYes
EventSensor Signal Processing for Defence Conference 2011 - London, United Kingdom
Duration: 27 Sept 201129 Sept 2011
https://digital-library.theiet.org/content/conferences/2011/004;jsessionid=54o7q15sa5s3.x-iet-live-01 (Proceedings)

Publication series

NameIET Seminar Digest
Number4
Volume2011

Conference

ConferenceSensor Signal Processing for Defence Conference 2011
Abbreviated titleSSPD 2011
Country/TerritoryUnited Kingdom
CityLondon
Period27/09/1129/09/11
Internet address

Cite this