Binaural Tracking of Multiple Moving Sources

Abstract

This paper addresses the problem of tracking multiple moving sources using binaural input. We observe that binaural cues are strongly correlated with source locations in time-frequency regions dominated by only one source. Based on this observation, we propose a novel tracking algorithm that integrates probabilities across reliable frequency channels in order to produce a likelihood function in the target space, which describes the azimuths of active sources at a particular time frame. Finally, a hidden Markov model (HMM) is employed to form continuous tracks and automatically detect the number of active sources across time. Experimental results are presented for two- and three-source scenarios. A comparison shows that our HMM model outperforms a Kalman filter based approach in tracking active sources across time. Our study represents a first step in addressing auditory scene analysis with moving sound sources.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
AD1001197

Entities

People

  • DeLiang Wang
  • Nicoleta Roman

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Computational Science
  • Computer Science
  • Cross Correlation
  • Data Association
  • Data Science
  • Databases
  • Detection
  • Ear
  • Hidden Markov Models
  • Information Science
  • Kalman Filters
  • Multiple Hypothesis Tracking
  • Probability
  • Statistical Algorithms
  • Stochastic Processes
  • Two Dimensional

Fields of Study

  • Engineering

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Radar Systems Engineering.
  • Speech Processing/Speech Recognition.

Technology Areas

  • Space
  • Space - Space Objects