Binaural tracking of multiple moving sources

Author

Roman, Nicoleta ; Wang, DeLiang

Author_Institution

Dept. of Comput. & Inf., Ohio State Univ., Columbus, OH, USA

Volume

5

fYear

2003

fDate

6-10 April 2003

Abstract

This paper presents a novel method for tracking the azimuth locations of multiple active sources based on binaural processing. Binaural cues are strongly correlated with source locations for spectral regions dominated by only one source. Therefore, this approach integrates reliable information across different frequency channels to produce a likelihood function in the target space. Finally, a hidden Markov model (HMM) is employed for forming continuous tracks and detecting the number of active sources across time. Experimental results are presented for simulated multi-source scenarios.

Keywords

hidden Markov models; maximum likelihood detection; source separation; tracking; HMM; azimuth locations; binaural tracking; continuous tracks; frequency channels; hidden Markov model; likelihood function; multiple moving sources; simulated multi-source scenarios; source locations; spectral regions; Azimuth; Cognitive science; Ear; Frequency; Hidden Markov models; Humans; Information science; Microphone arrays; Position measurement; Target tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1199890

Filename

1199890