Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index

Andreas Jonas Fuglsig; Jan Østergaard; Jesper Jensen; Lars Søndergaard Bertelsen; Peter Bank Mariager; Zheng-Hua Tan

doi:10.1109/ICASSP43922.2022.9746170

Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index

Andreas Jonas Fuglsig, Jan Østergaard, Jesper Jensen, Lars Søndergaard Bertelsen, Peter Bank Mariager, Zheng-Hua Tan

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

4 Citations (Scopus)

94 Downloads (Pure)

Abstract

This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been shown that an optimal solution to this problem requires the consideration of the noise sources in both environments jointly. However, the existing optimal mutual information based method requires a complicated system model that includes natural speech variations, and relies on approximations and assumptions of the underlying signal distributions. In this paper, we propose to use a simpler signal model and optimize speech intelligibility based on the Approximated Speech Intelligibility Index (ASII). We derive a closed-form solution to the joint far- and near-end speech enhancement problem that is independent of the marginal distribution of signal coefficients, and that achieves similar performance to existing work. In addition, we do not need to model or optimize for natural speech variations.

Original language	English
Title of host publication	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Number of pages	5
Place of Publication	Singapore
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	2022
Pages	7752-7756
Article number	9746170
ISBN (Print)	9781665405416
ISBN (Electronic)	9781665405409
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746170
Publication status	Published - 2022
Event	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore Duration: 23 May 2022 → 27 May 2022

Conference

Conference	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/Territory	Singapore
City	Virtual, Online
Period	23/05/2022 → 27/05/2022
Sponsor	Chinese and Oriental Languages Information Processing Society (COLPIS), Singapore Exhibition and Convention Bureau, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), The Institute of Electrical and Electronics Engineers Signal Processing Society

Series	I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN	1520-6149

Keywords

ASII
beamformer
Multi-microphone
speech intelligibility enhancement

Access to Document

10.1109/ICASSP43922.2022.9746170

Accepted author manuscriptAccepted author manuscript, 591 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Fuglsig, A. J., Østergaard, J., Jensen, J., Søndergaard Bertelsen, L., Mariager, P. B., & Tan, Z.-H. (2022). Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7752-7756). Article 9746170 IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/ICASSP43922.2022.9746170

Fuglsig, Andreas Jonas ; Østergaard, Jan ; Jensen, Jesper et al. / Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore : IEEE (Institute of Electrical and Electronics Engineers), 2022. pp. 7752-7756 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

@inproceedings{6c5e9c1a05424a3a92743ca81b0a0612,

title = "Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index",

abstract = "This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been shown that an optimal solution to this problem requires the consideration of the noise sources in both environments jointly. However, the existing optimal mutual information based method requires a complicated system model that includes natural speech variations, and relies on approximations and assumptions of the underlying signal distributions. In this paper, we propose to use a simpler signal model and optimize speech intelligibility based on the Approximated Speech Intelligibility Index (ASII). We derive a closed-form solution to the joint far- and near-end speech enhancement problem that is independent of the marginal distribution of signal coefficients, and that achieves similar performance to existing work. In addition, we do not need to model or optimize for natural speech variations.",

keywords = "Speech Enhancement, Noise Reduction, Intelligibility Enhancement, Beamforming, ASII, beamformer, Multi-microphone, speech intelligibility enhancement",

author = "Fuglsig, {Andreas Jonas} and Jan {\O}stergaard and Jesper Jensen and {S{\o}ndergaard Bertelsen}, Lars and Mariager, {Peter Bank} and Zheng-Hua Tan",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746170",

language = "English",

isbn = "9781665405416",

series = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

pages = "7752--7756",

booktitle = "ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

}

Fuglsig, AJ , Østergaard, J , Jensen, J, Søndergaard Bertelsen, L, Mariager, PB & Tan, Z-H 2022, Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index. in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 9746170, IEEE (Institute of Electrical and Electronics Engineers), Singapore, I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 7752-7756, 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, Virtual, Online, Singapore, 23/05/2022. https://doi.org/10.1109/ICASSP43922.2022.9746170

Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index. / Fuglsig, Andreas Jonas ; Østergaard, Jan ; Jensen, Jesper et al.
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore: IEEE (Institute of Electrical and Electronics Engineers), 2022. p. 7752-7756 9746170 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index

AU - Fuglsig, Andreas Jonas

AU - Østergaard, Jan

AU - Jensen, Jesper

AU - Søndergaard Bertelsen, Lars

AU - Mariager, Peter Bank

AU - Tan, Zheng-Hua

PY - 2022

Y1 - 2022

N2 - This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been shown that an optimal solution to this problem requires the consideration of the noise sources in both environments jointly. However, the existing optimal mutual information based method requires a complicated system model that includes natural speech variations, and relies on approximations and assumptions of the underlying signal distributions. In this paper, we propose to use a simpler signal model and optimize speech intelligibility based on the Approximated Speech Intelligibility Index (ASII). We derive a closed-form solution to the joint far- and near-end speech enhancement problem that is independent of the marginal distribution of signal coefficients, and that achieves similar performance to existing work. In addition, we do not need to model or optimize for natural speech variations.

AB - This paper considers speech enhancement of signals picked up in one noisy environment which must be presented to a listener in another noisy environment. Recently, it has been shown that an optimal solution to this problem requires the consideration of the noise sources in both environments jointly. However, the existing optimal mutual information based method requires a complicated system model that includes natural speech variations, and relies on approximations and assumptions of the underlying signal distributions. In this paper, we propose to use a simpler signal model and optimize speech intelligibility based on the Approximated Speech Intelligibility Index (ASII). We derive a closed-form solution to the joint far- and near-end speech enhancement problem that is independent of the marginal distribution of signal coefficients, and that achieves similar performance to existing work. In addition, we do not need to model or optimize for natural speech variations.

KW - Speech Enhancement

KW - Noise Reduction

KW - Intelligibility Enhancement

KW - Beamforming

KW - ASII

KW - beamformer

KW - Multi-microphone

KW - speech intelligibility enhancement

UR - http://www.scopus.com/inward/record.url?scp=85131246950&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746170

DO - 10.1109/ICASSP43922.2022.9746170

M3 - Article in proceeding

SN - 9781665405416

T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SP - 7752

EP - 7756

BT - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE (Institute of Electrical and Electronics Engineers)

CY - Singapore

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 23 May 2022 through 27 May 2022

ER -

Fuglsig AJ , Østergaard J , Jensen J, Søndergaard Bertelsen L, Mariager PB , Tan ZH. Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapore: IEEE (Institute of Electrical and Electronics Engineers). 2022. p. 7752-7756. 9746170. (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings). doi: 10.1109/ICASSP43922.2022.9746170

Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Adaptive Multi- microphone Enhancement for Wireless Speech Communications

Joint Far- and Near-end Speech and Listening Enhancement with a Minimum Processing Perspective

Cite this

Joint Far- and Near-End Speech Intelligibility Enhancement Based on the Approximated Speech Intelligibility Index

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Projects

Adaptive Multi- microphone Enhancement for Wireless Speech Communications

Research output

Joint Far- and Near-end Speech and Listening Enhancement with a Minimum Processing Perspective

Cite this