Improved Intelligibility Prediction in the Modulation Domain

Ahmed Alghamdi; Wai Yip Chan; Daniel Fogerty; Jesper Jensen

doi:10.1109/WASPAA52581.2021.9632766

Improved Intelligibility Prediction in the Modulation Domain

Ahmed Alghamdi, Wai Yip Chan, Daniel Fogerty, Jesper Jensen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

sEPSMcorr is a recently proposed intelligibility measure that combines a modulation domain auditory model with a correlation similarity metric inspired by the STOI measure. In this paper, we aim at improving the overall performance of sEPSMcorr, particularly in modulated noise conditions. We propose to improve its auditory model and use a segmentation scheme and similarity metric adapted from the extended STOI measure that works better than STOI with modulated noise. Performance evaluation against subjective data shows the modified measure is able to predict intelligibility much better than the original version in conditions involving modulated noise, nonlinear processing, and reverberation. The modified sEPSMcorr also has better overall performance than several baseline intelligibility measures, especially in modulated noise conditions. Additionally, we study the contribution of the proposed modifications to performance by evaluating variants of the modified measure where subsets of the modifications are in effect.

Original language	English (US)
Title of host publication	2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	16-20
Number of pages	5
ISBN (Electronic)	9781665448703
DOIs	https://doi.org/10.1109/WASPAA52581.2021.9632766
State	Published - 2021
Externally published	Yes
Event	2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021 - New Paltz, United States Duration: Oct 17 2021 → Oct 20 2021

Publication series

Name	IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Volume	2021-October
ISSN (Print)	1931-1168
ISSN (Electronic)	1947-1629

Conference

Conference	2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021
Country/Territory	United States
City	New Paltz
Period	10/17/21 → 10/20/21

Keywords

speech intelligibility
temporal modulation

ASJC Scopus subject areas

Electrical and Electronic Engineering
Computer Science Applications

Online availability

10.1109/WASPAA52581.2021.9632766

Library availability

Discover UIUC Full Text

Cite this

Alghamdi, A., Chan, W. Y., Fogerty, D., & Jensen, J. (2021). Improved Intelligibility Prediction in the Modulation Domain. In 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021 (pp. 16-20). (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics; Vol. 2021-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WASPAA52581.2021.9632766

Improved Intelligibility Prediction in the Modulation Domain. / Alghamdi, Ahmed; Chan, Wai Yip; Fogerty, Daniel et al.
2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 16-20 (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics; Vol. 2021-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Alghamdi, A, Chan, WY, Fogerty, D & Jensen, J 2021, Improved Intelligibility Prediction in the Modulation Domain. in 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, vol. 2021-October, Institute of Electrical and Electronics Engineers Inc., pp. 16-20, 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021, New Paltz, United States, 10/17/21. https://doi.org/10.1109/WASPAA52581.2021.9632766

Alghamdi A, Chan WY, Fogerty D, Jensen J. Improved Intelligibility Prediction in the Modulation Domain. In 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 16-20. (IEEE Workshop on Applications of Signal Processing to Audio and Acoustics). doi: 10.1109/WASPAA52581.2021.9632766

@inproceedings{0e9c0910bd4342b9b51d5f675f487d66,

title = "Improved Intelligibility Prediction in the Modulation Domain",

abstract = "sEPSMcorr is a recently proposed intelligibility measure that combines a modulation domain auditory model with a correlation similarity metric inspired by the STOI measure. In this paper, we aim at improving the overall performance of sEPSMcorr, particularly in modulated noise conditions. We propose to improve its auditory model and use a segmentation scheme and similarity metric adapted from the extended STOI measure that works better than STOI with modulated noise. Performance evaluation against subjective data shows the modified measure is able to predict intelligibility much better than the original version in conditions involving modulated noise, nonlinear processing, and reverberation. The modified sEPSMcorr also has better overall performance than several baseline intelligibility measures, especially in modulated noise conditions. Additionally, we study the contribution of the proposed modifications to performance by evaluating variants of the modified measure where subsets of the modifications are in effect.",

keywords = "speech intelligibility, temporal modulation",

author = "Ahmed Alghamdi and Chan, {Wai Yip} and Daniel Fogerty and Jesper Jensen",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021 ; Conference date: 17-10-2021 Through 20-10-2021",

year = "2021",

doi = "10.1109/WASPAA52581.2021.9632766",

language = "English (US)",

series = "IEEE Workshop on Applications of Signal Processing to Audio and Acoustics",

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

pages = "16--20",

booktitle = "2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021",

address = "United States",

}

TY - GEN

T1 - Improved Intelligibility Prediction in the Modulation Domain

AU - Alghamdi, Ahmed

AU - Chan, Wai Yip

AU - Fogerty, Daniel

AU - Jensen, Jesper

PY - 2021

Y1 - 2021

N2 - sEPSMcorr is a recently proposed intelligibility measure that combines a modulation domain auditory model with a correlation similarity metric inspired by the STOI measure. In this paper, we aim at improving the overall performance of sEPSMcorr, particularly in modulated noise conditions. We propose to improve its auditory model and use a segmentation scheme and similarity metric adapted from the extended STOI measure that works better than STOI with modulated noise. Performance evaluation against subjective data shows the modified measure is able to predict intelligibility much better than the original version in conditions involving modulated noise, nonlinear processing, and reverberation. The modified sEPSMcorr also has better overall performance than several baseline intelligibility measures, especially in modulated noise conditions. Additionally, we study the contribution of the proposed modifications to performance by evaluating variants of the modified measure where subsets of the modifications are in effect.

AB - sEPSMcorr is a recently proposed intelligibility measure that combines a modulation domain auditory model with a correlation similarity metric inspired by the STOI measure. In this paper, we aim at improving the overall performance of sEPSMcorr, particularly in modulated noise conditions. We propose to improve its auditory model and use a segmentation scheme and similarity metric adapted from the extended STOI measure that works better than STOI with modulated noise. Performance evaluation against subjective data shows the modified measure is able to predict intelligibility much better than the original version in conditions involving modulated noise, nonlinear processing, and reverberation. The modified sEPSMcorr also has better overall performance than several baseline intelligibility measures, especially in modulated noise conditions. Additionally, we study the contribution of the proposed modifications to performance by evaluating variants of the modified measure where subsets of the modifications are in effect.

KW - speech intelligibility

KW - temporal modulation

UR - http://www.scopus.com/inward/record.url?scp=85123399346&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85123399346&partnerID=8YFLogxK

U2 - 10.1109/WASPAA52581.2021.9632766

DO - 10.1109/WASPAA52581.2021.9632766

M3 - Conference contribution

AN - SCOPUS:85123399346

T3 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

SP - 16

EP - 20

BT - 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2021

Y2 - 17 October 2021 through 20 October 2021

ER -

Improved Intelligibility Prediction in the Modulation Domain

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this