Robust DOA estimation of multiple speech sources

Nguyen Thi Ngoc Tho, Shengkui Zhao, Douglas L Jones

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

Abstract

It is challenging to determine the directions of arrival of speech signals when there are fewer sensors than sources, particularly in noisy and reverberant environments. The coherence test by Mohan et al. exploits the time-frequency sparseness of non-stationary speech signals to select more relevant time-frequency bins to estimate directions of arrival. With no prior knowledge about the incoming sources, this work proposes a combination of noise-floor tracking, onset detection and a coherence test to robustly identify time-frequency bins where only one source is dominant. After that, the largest eigenvectors of covariance matrices corresponding to these bins are clustered and the directions of arrival of the sources are estimated based on the cluster centroids. Simulation and experimental results show that this method is able to localize 8 sources with small errors using only 3 omnidirectional microphones. The proposed method is robust to background noise and reverberation.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2287-2291
Number of pages5
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period5/4/145/9/14

Fingerprint

Direction of arrival
Bins
Reverberation
Microphones
Covariance matrix
Acoustic noise
Eigenvalues and eigenfunctions
Sensors

Keywords

  • coherence test
  • direction of arrival estimation
  • eigenvector
  • microphone array
  • time-frequency

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Tho, N. T. N., Zhao, S., & Jones, D. L. (2014). Robust DOA estimation of multiple speech sources. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 (pp. 2287-2291). [6854007] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6854007

Robust DOA estimation of multiple speech sources. / Tho, Nguyen Thi Ngoc; Zhao, Shengkui; Jones, Douglas L.

2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2287-2291 6854007.

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

Tho, NTN, Zhao, S & Jones, DL 2014, Robust DOA estimation of multiple speech sources. in 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014., 6854007, Institute of Electrical and Electronics Engineers Inc., pp. 2287-2291, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 5/4/14. https://doi.org/10.1109/ICASSP.2014.6854007
Tho NTN, Zhao S, Jones DL. Robust DOA estimation of multiple speech sources. In 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 2287-2291. 6854007 https://doi.org/10.1109/ICASSP.2014.6854007
Tho, Nguyen Thi Ngoc ; Zhao, Shengkui ; Jones, Douglas L. / Robust DOA estimation of multiple speech sources. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 2287-2291
@inproceedings{74eadf17ffc14b78853242c8c8429ae1,
title = "Robust DOA estimation of multiple speech sources",
abstract = "It is challenging to determine the directions of arrival of speech signals when there are fewer sensors than sources, particularly in noisy and reverberant environments. The coherence test by Mohan et al. exploits the time-frequency sparseness of non-stationary speech signals to select more relevant time-frequency bins to estimate directions of arrival. With no prior knowledge about the incoming sources, this work proposes a combination of noise-floor tracking, onset detection and a coherence test to robustly identify time-frequency bins where only one source is dominant. After that, the largest eigenvectors of covariance matrices corresponding to these bins are clustered and the directions of arrival of the sources are estimated based on the cluster centroids. Simulation and experimental results show that this method is able to localize 8 sources with small errors using only 3 omnidirectional microphones. The proposed method is robust to background noise and reverberation.",
keywords = "coherence test, direction of arrival estimation, eigenvector, microphone array, time-frequency",
author = "Tho, {Nguyen Thi Ngoc} and Shengkui Zhao and Jones, {Douglas L}",
year = "2014",
doi = "10.1109/ICASSP.2014.6854007",
language = "English (US)",
isbn = "9781479928927",
pages = "2287--2291",
booktitle = "2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Robust DOA estimation of multiple speech sources

AU - Tho, Nguyen Thi Ngoc

AU - Zhao, Shengkui

AU - Jones, Douglas L

PY - 2014

Y1 - 2014

N2 - It is challenging to determine the directions of arrival of speech signals when there are fewer sensors than sources, particularly in noisy and reverberant environments. The coherence test by Mohan et al. exploits the time-frequency sparseness of non-stationary speech signals to select more relevant time-frequency bins to estimate directions of arrival. With no prior knowledge about the incoming sources, this work proposes a combination of noise-floor tracking, onset detection and a coherence test to robustly identify time-frequency bins where only one source is dominant. After that, the largest eigenvectors of covariance matrices corresponding to these bins are clustered and the directions of arrival of the sources are estimated based on the cluster centroids. Simulation and experimental results show that this method is able to localize 8 sources with small errors using only 3 omnidirectional microphones. The proposed method is robust to background noise and reverberation.

AB - It is challenging to determine the directions of arrival of speech signals when there are fewer sensors than sources, particularly in noisy and reverberant environments. The coherence test by Mohan et al. exploits the time-frequency sparseness of non-stationary speech signals to select more relevant time-frequency bins to estimate directions of arrival. With no prior knowledge about the incoming sources, this work proposes a combination of noise-floor tracking, onset detection and a coherence test to robustly identify time-frequency bins where only one source is dominant. After that, the largest eigenvectors of covariance matrices corresponding to these bins are clustered and the directions of arrival of the sources are estimated based on the cluster centroids. Simulation and experimental results show that this method is able to localize 8 sources with small errors using only 3 omnidirectional microphones. The proposed method is robust to background noise and reverberation.

KW - coherence test

KW - direction of arrival estimation

KW - eigenvector

KW - microphone array

KW - time-frequency

UR - http://www.scopus.com/inward/record.url?scp=84905251108&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905251108&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6854007

DO - 10.1109/ICASSP.2014.6854007

M3 - Conference contribution

AN - SCOPUS:84905251108

SN - 9781479928927

SP - 2287

EP - 2291

BT - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -