A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction

Amin Edraki; Wai Yip Chan; Jesper Jensen; Daniel Fogerty

doi:10.21437/Interspeech.2021-605

A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction

Amin Edraki, Wai Yip Chan, Jesper Jensen, Daniel Fogerty

Speech and Hearing Science

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

Abstract

We propose a monaural intrusive speech intelligibility prediction (SIP) algorithm called STGI based on detecting glimpses in short-time segments in a spectro-temporal modulation decomposition of the input speech signals. Unlike existing glimpse-based SIP methods, the application of STGI is not limited to additive uncorrelated noise; STGI can be employed in a broad range of degradation conditions. Our results show that STGI performs consistently well across 15 datasets covering degradation conditions including modulated noise, noise reduction processing, reverberation, near-end listening enhancement, checkerboard noise, and gated noise.

Original language	English (US)
Title of host publication	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Publisher	International Speech Communication Association
Pages	2738-2742
Number of pages	5
ISBN (Electronic)	9781713836902
DOIs	https://doi.org/10.21437/Interspeech.2021-605
State	Published - 2021
Event	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Czech Republic Duration: Aug 30 2021 → Sep 3 2021

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	4
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Country/Territory	Czech Republic
City	Brno
Period	8/30/21 → 9/3/21

Keywords

Glimpsing
Spectro-temporal modulation
Speech intelligibility
Speech quality model

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modeling and Simulation

Online availability

10.21437/Interspeech.2021-605

Library availability

Discover UIUC Full Text

Cite this

Edraki, A., Chan, W. Y., Jensen, J., & Fogerty, D. (2021). A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction. In 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 (pp. 2738-2742). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 4). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2021-605

A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction. / Edraki, Amin; Chan, Wai Yip; Jensen, Jesper et al.
22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association, 2021. p. 2738-2742 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 4).

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

Edraki, A, Chan, WY, Jensen, J & Fogerty, D 2021, A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction. in 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 4, International Speech Communication Association, pp. 2738-2742, 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021, Brno, Czech Republic, 8/30/21. https://doi.org/10.21437/Interspeech.2021-605

Edraki A, Chan WY, Jensen J, Fogerty D. A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction. In 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association. 2021. p. 2738-2742. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2021-605

Edraki, Amin ; Chan, Wai Yip ; Jensen, Jesper et al. / A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction. 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association, 2021. pp. 2738-2742 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{90d177a3c30d48d093eda007183b34f6,

title = "A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction",

abstract = "We propose a monaural intrusive speech intelligibility prediction (SIP) algorithm called STGI based on detecting glimpses in short-time segments in a spectro-temporal modulation decomposition of the input speech signals. Unlike existing glimpse-based SIP methods, the application of STGI is not limited to additive uncorrelated noise; STGI can be employed in a broad range of degradation conditions. Our results show that STGI performs consistently well across 15 datasets covering degradation conditions including modulated noise, noise reduction processing, reverberation, near-end listening enhancement, checkerboard noise, and gated noise.",

keywords = "Glimpsing, Spectro-temporal modulation, Speech intelligibility, Speech quality model",

author = "Amin Edraki and Chan, {Wai Yip} and Jesper Jensen and Daniel Fogerty",

note = "Publisher Copyright: Copyright {\textcopyright} 2021 ISCA.; 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

doi = "10.21437/Interspeech.2021-605",

language = "English (US)",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech Communication Association",

pages = "2738--2742",

booktitle = "22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021",

}

TY - GEN

T1 - A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction

AU - Edraki, Amin

AU - Chan, Wai Yip

AU - Jensen, Jesper

AU - Fogerty, Daniel

PY - 2021

Y1 - 2021

N2 - We propose a monaural intrusive speech intelligibility prediction (SIP) algorithm called STGI based on detecting glimpses in short-time segments in a spectro-temporal modulation decomposition of the input speech signals. Unlike existing glimpse-based SIP methods, the application of STGI is not limited to additive uncorrelated noise; STGI can be employed in a broad range of degradation conditions. Our results show that STGI performs consistently well across 15 datasets covering degradation conditions including modulated noise, noise reduction processing, reverberation, near-end listening enhancement, checkerboard noise, and gated noise.

AB - We propose a monaural intrusive speech intelligibility prediction (SIP) algorithm called STGI based on detecting glimpses in short-time segments in a spectro-temporal modulation decomposition of the input speech signals. Unlike existing glimpse-based SIP methods, the application of STGI is not limited to additive uncorrelated noise; STGI can be employed in a broad range of degradation conditions. Our results show that STGI performs consistently well across 15 datasets covering degradation conditions including modulated noise, noise reduction processing, reverberation, near-end listening enhancement, checkerboard noise, and gated noise.

KW - Glimpsing

KW - Spectro-temporal modulation

KW - Speech intelligibility

KW - Speech quality model

UR - http://www.scopus.com/inward/record.url?scp=85119186065&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119186065&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2021-605

DO - 10.21437/Interspeech.2021-605

M3 - Conference contribution

AN - SCOPUS:85119186065

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 2738

EP - 2742

BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021

PB - International Speech Communication Association

T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

A spectro-temporal glimpsing index (STGI) for speech intelligibility prediction

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this