Microphone array beamforming approach to blind speech separation

Authors:
Ivan Himawan;Iain McCowan;Mike Lincoln
Affiliations:
Queensland University of Technology, Brisbane, QLD, Australia and Centre for Speech Technology Research, Edinburgh, United Kingdom;Queensland University of Technology, Brisbane, QLD, Australia and CSIRO e-HEALTH Research Centre, Brisbane, QLD, Australia;Centre for Speech Technology Research, Edinburgh, United Kingdom
Venue:
MLMI'07 Proceedings of the 4th international conference on Machine learning for multimodal interaction
Year:
2007

Citing 4
Cited 1

The meeting project at ICSI

HLT '01 Proceedings of the first international conference on Human language technology research
The ICSI-SRI spring 2006 meeting recognition system

MLMI'06 Proceedings of the Third international conference on Machine Learning for Multimodal Interaction
Microphone Array Shape Calibration in Diffuse Noise Fields

IEEE Transactions on Audio, Speech, and Language Processing
Speech Enhancement and Recognition in Meetings With an Audio–Visual Sensor Array

IEEE Transactions on Audio, Speech, and Language Processing

The PASCAL CHiME speech separation and recognition challenge

Computer Speech and Language

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a microphone array beamforming approach to blind speech separation. Unlike previous beamforming approaches, our system does not require a-priori knowledge of the microphone placement and speaker location, making the system directly comparable other blind source separation methods which require no prior knowledge of recording conditions. Microphone location is automatically estimated using an assumed noise field model, and speaker locations are estimated using cross correlation based methods. The system is evaluated on the data provided for the PASCAL Speech Separation Challenge 2 (SSC2), achieving a word error rate of 58% on the evaluation set.