Sound source separation by using matched beamforming and time-frequency masking

Jounghoon Beh, Taekjin Lee, David Han, Hanseok Ko

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

2 Citations (Scopus)

Abstract

This paper proposes a two-stage algorithm to separate two sound sources by using matched beamforming and time-frequency masking techniques. At first, beamforming was used to separate the sound mixtures back to the original sources while preserving the original contents to the maximum extent. The residual interference was then suppressed by the time-frequency masking technique. A sequential least squares method was used in developing a matched beamformer to estimate the relative transfer function (RTF). From experimental results, it has been shown that the proposed method exhibits improved performance in sound source separation compared to conventional methods. Signal enhanced factor (SEF) was improved by an average of 8.39 dB over the baseline.

Original languageEnglish
Title of host publicationIEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings
Pages458-463
Number of pages6
DOIs
Publication statusPublished - 2010 Dec 1
Event23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Taipei, Taiwan, Province of China
Duration: 2010 Oct 182010 Oct 22

Other

Other23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010
CountryTaiwan, Province of China
CityTaipei
Period10/10/1810/10/22

Fingerprint

Source separation
Beamforming
Acoustic waves
Transfer functions

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Beh, J., Lee, T., Han, D., & Ko, H. (2010). Sound source separation by using matched beamforming and time-frequency masking. In IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings (pp. 458-463). [5652512] https://doi.org/10.1109/IROS.2010.5652512

Sound source separation by using matched beamforming and time-frequency masking. / Beh, Jounghoon; Lee, Taekjin; Han, David; Ko, Hanseok.

IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. p. 458-463 5652512.

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

Beh, J, Lee, T, Han, D & Ko, H 2010, Sound source separation by using matched beamforming and time-frequency masking. in IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings., 5652512, pp. 458-463, 23rd IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010, Taipei, Taiwan, Province of China, 10/10/18. https://doi.org/10.1109/IROS.2010.5652512
Beh J, Lee T, Han D, Ko H. Sound source separation by using matched beamforming and time-frequency masking. In IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. p. 458-463. 5652512 https://doi.org/10.1109/IROS.2010.5652512
Beh, Jounghoon ; Lee, Taekjin ; Han, David ; Ko, Hanseok. / Sound source separation by using matched beamforming and time-frequency masking. IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings. 2010. pp. 458-463
@inproceedings{a014201bbab94526b186b2832b13eea1,
title = "Sound source separation by using matched beamforming and time-frequency masking",
abstract = "This paper proposes a two-stage algorithm to separate two sound sources by using matched beamforming and time-frequency masking techniques. At first, beamforming was used to separate the sound mixtures back to the original sources while preserving the original contents to the maximum extent. The residual interference was then suppressed by the time-frequency masking technique. A sequential least squares method was used in developing a matched beamformer to estimate the relative transfer function (RTF). From experimental results, it has been shown that the proposed method exhibits improved performance in sound source separation compared to conventional methods. Signal enhanced factor (SEF) was improved by an average of 8.39 dB over the baseline.",
author = "Jounghoon Beh and Taekjin Lee and David Han and Hanseok Ko",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/IROS.2010.5652512",
language = "English",
isbn = "9781424466757",
pages = "458--463",
booktitle = "IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings",

}

TY - GEN

T1 - Sound source separation by using matched beamforming and time-frequency masking

AU - Beh, Jounghoon

AU - Lee, Taekjin

AU - Han, David

AU - Ko, Hanseok

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper proposes a two-stage algorithm to separate two sound sources by using matched beamforming and time-frequency masking techniques. At first, beamforming was used to separate the sound mixtures back to the original sources while preserving the original contents to the maximum extent. The residual interference was then suppressed by the time-frequency masking technique. A sequential least squares method was used in developing a matched beamformer to estimate the relative transfer function (RTF). From experimental results, it has been shown that the proposed method exhibits improved performance in sound source separation compared to conventional methods. Signal enhanced factor (SEF) was improved by an average of 8.39 dB over the baseline.

AB - This paper proposes a two-stage algorithm to separate two sound sources by using matched beamforming and time-frequency masking techniques. At first, beamforming was used to separate the sound mixtures back to the original sources while preserving the original contents to the maximum extent. The residual interference was then suppressed by the time-frequency masking technique. A sequential least squares method was used in developing a matched beamformer to estimate the relative transfer function (RTF). From experimental results, it has been shown that the proposed method exhibits improved performance in sound source separation compared to conventional methods. Signal enhanced factor (SEF) was improved by an average of 8.39 dB over the baseline.

UR - http://www.scopus.com/inward/record.url?scp=78651513629&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651513629&partnerID=8YFLogxK

U2 - 10.1109/IROS.2010.5652512

DO - 10.1109/IROS.2010.5652512

M3 - Conference contribution

AN - SCOPUS:78651513629

SN - 9781424466757

SP - 458

EP - 463

BT - IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010 - Conference Proceedings

ER -