Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures

Karn Watcharasupat; Anh H.T. Nguyen; Ching Hui Ooi; Andy W.H. Khong

doi:10.1109/ICASSP39728.2021.9414336

Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures

Karn Watcharasupat, Anh H.T. Nguyen, Ching Hui Ooi, Andy W.H. Khong

Nanyang Technological University

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.

Original language	English
Pages (from-to)	4485-4489
Number of pages	5
Journal	Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Volume	2021-June
DOIs	https://doi.org/10.1109/ICASSP39728.2021.9414336
Publication status	Published - 2021
Externally published	Yes
Event	2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada Duration: Jun 6 2021 → Jun 11 2021

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

ASJC Scopus Subject Areas

Software
Signal Processing
Electrical and Electronic Engineering

Keywords

Blind source separation
Directional clustering
Lehmer mean
Microphone array
Sparse filtering

Access to Document

10.1109/ICASSP39728.2021.9414336

Cite this

@article{8d056c4c7e274e37bb846e5f2792dc5e,

title = "Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures",

abstract = "In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.",

keywords = "Blind source separation, Directional clustering, Lehmer mean, Microphone array, Sparse filtering",

author = "Karn Watcharasupat and Nguyen, {Anh H.T.} and Ooi, {Ching Hui} and Khong, {Andy W.H.}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 ; Conference date: 06-06-2021 Through 11-06-2021",

year = "2021",

doi = "10.1109/ICASSP39728.2021.9414336",

language = "English",

volume = "2021-June",

pages = "4485--4489",

journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

issn = "1520-6149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures. / Watcharasupat, Karn; Nguyen, Anh H.T.; Ooi, Ching Hui et al.
In: Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 2021-June, 2021, p. 4485-4489.

Research output: Contribution to journal › Conference article › peer-review

TY - JOUR

T1 - Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures

AU - Watcharasupat, Karn

AU - Nguyen, Anh H.T.

AU - Ooi, Ching Hui

AU - Khong, Andy W.H.

PY - 2021

Y1 - 2021

N2 - In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.

AB - In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.

KW - Blind source separation

KW - Directional clustering

KW - Lehmer mean

KW - Microphone array

KW - Sparse filtering

UR - http://www.scopus.com/inward/record.url?scp=85115107451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85115107451&partnerID=8YFLogxK

U2 - 10.1109/ICASSP39728.2021.9414336

DO - 10.1109/ICASSP39728.2021.9414336

M3 - Conference article

AN - SCOPUS:85115107451

SN - 1520-6149

VL - 2021-June

SP - 4485

EP - 4489

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021

Y2 - 6 June 2021 through 11 June 2021

ER -

Directional sparse filtering using weighted lehmer mean for blind separation of unbalanced speech mixtures

Abstract

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this