Automatic detection of syllabic nuclei using acoustic measures

G. Kawai; J. Van Santen

doi:10.1109/WSS.2002.1224368

Automatic detection of syllabic nuclei using acoustic measures

G. Kawai, J. Van Santen

Institute on Development & Disability

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

2 Scopus citations

Abstract

This paper describes a method for detecting syllabic nuclei from English utterances on a frame-by-frame basis using bandpass-filtered acoustic energy measurements. No knowledge of the utterance's phonetic composition is used. In the training phase, phones in English utterances read by a female speaker were assigned rank-ordered sonority values. These sonority values were predicted using multiple linear regression where the predictor variables were bandpass-filtered acoustic energy values at the phone's central region. Results show that (1) syllabic nuclei are identified at over 60 percent accuracy, and (2) speech rate, defined as syllabic nuclei per unit time, is estimated at over 80 percent accuracy.

Original language	English (US)
Title of host publication	Proceedings of 2002 IEEE Workshop on Speech Synthesis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	39-42
Number of pages	4
ISBN (Electronic)	0780373952, 9780780373952
DOIs	https://doi.org/10.1109/WSS.2002.1224368
State	Published - 2002
Event	2002 IEEE Workshop on Speech Synthesis - Santa Monica, United States Duration: Sep 11 2002 → Sep 13 2002

Publication series

Name	Proceedings of 2002 IEEE Workshop on Speech Synthesis

Other

Other	2002 IEEE Workshop on Speech Synthesis
Country	United States
City	Santa Monica
Period	9/11/02 → 9/13/02

Keywords

sonority
speech energy
speech rate
syllabic nuclei

ASJC Scopus subject areas

Language and Linguistics
Cultural Studies

Access to Document

10.1109/WSS.2002.1224368

Fingerprint Dive into the research topics of 'Automatic detection of syllabic nuclei using acoustic measures'. Together they form a unique fingerprint.

Cite this

Automatic detection of syllabic nuclei using acoustic measures. / Kawai, G.; Van Santen, J.

Proceedings of 2002 IEEE Workshop on Speech Synthesis. Institute of Electrical and Electronics Engineers Inc., 2002. p. 39-42 1224368 (Proceedings of 2002 IEEE Workshop on Speech Synthesis).

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

Kawai, G & Van Santen, J 2002, Automatic detection of syllabic nuclei using acoustic measures. in Proceedings of 2002 IEEE Workshop on Speech Synthesis., 1224368, Proceedings of 2002 IEEE Workshop on Speech Synthesis, Institute of Electrical and Electronics Engineers Inc., pp. 39-42, 2002 IEEE Workshop on Speech Synthesis, Santa Monica, United States, 9/11/02. https://doi.org/10.1109/WSS.2002.1224368

@inproceedings{2184fede6e304c8d8d18df17a79dd617,

title = "Automatic detection of syllabic nuclei using acoustic measures",

abstract = "This paper describes a method for detecting syllabic nuclei from English utterances on a frame-by-frame basis using bandpass-filtered acoustic energy measurements. No knowledge of the utterance's phonetic composition is used. In the training phase, phones in English utterances read by a female speaker were assigned rank-ordered sonority values. These sonority values were predicted using multiple linear regression where the predictor variables were bandpass-filtered acoustic energy values at the phone's central region. Results show that (1) syllabic nuclei are identified at over 60 percent accuracy, and (2) speech rate, defined as syllabic nuclei per unit time, is estimated at over 80 percent accuracy.",

keywords = "sonority, speech energy, speech rate, syllabic nuclei",

author = "G. Kawai and {Van Santen}, J.",

note = "Funding Information: This research was conducted with support from NSF grants 0117911 {"}Making Dysarthric Speech Intelligible{"} and 0082718 {"}Modeling Degree of Articulation for Speech Synthesis{"}, as well as support from Intel and NTT.; 2002 IEEE Workshop on Speech Synthesis ; Conference date: 11-09-2002 Through 13-09-2002",

year = "2002",

doi = "10.1109/WSS.2002.1224368",

language = "English (US)",

series = "Proceedings of 2002 IEEE Workshop on Speech Synthesis",

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

pages = "39--42",

booktitle = "Proceedings of 2002 IEEE Workshop on Speech Synthesis",

}

TY - GEN

T1 - Automatic detection of syllabic nuclei using acoustic measures

AU - Kawai, G.

AU - Van Santen, J.

N1 - Funding Information: This research was conducted with support from NSF grants 0117911 "Making Dysarthric Speech Intelligible" and 0082718 "Modeling Degree of Articulation for Speech Synthesis", as well as support from Intel and NTT.

PY - 2002

Y1 - 2002

N2 - This paper describes a method for detecting syllabic nuclei from English utterances on a frame-by-frame basis using bandpass-filtered acoustic energy measurements. No knowledge of the utterance's phonetic composition is used. In the training phase, phones in English utterances read by a female speaker were assigned rank-ordered sonority values. These sonority values were predicted using multiple linear regression where the predictor variables were bandpass-filtered acoustic energy values at the phone's central region. Results show that (1) syllabic nuclei are identified at over 60 percent accuracy, and (2) speech rate, defined as syllabic nuclei per unit time, is estimated at over 80 percent accuracy.

AB - This paper describes a method for detecting syllabic nuclei from English utterances on a frame-by-frame basis using bandpass-filtered acoustic energy measurements. No knowledge of the utterance's phonetic composition is used. In the training phase, phones in English utterances read by a female speaker were assigned rank-ordered sonority values. These sonority values were predicted using multiple linear regression where the predictor variables were bandpass-filtered acoustic energy values at the phone's central region. Results show that (1) syllabic nuclei are identified at over 60 percent accuracy, and (2) speech rate, defined as syllabic nuclei per unit time, is estimated at over 80 percent accuracy.

KW - sonority

KW - speech energy

KW - speech rate

KW - syllabic nuclei

UR - http://www.scopus.com/inward/record.url?scp=84966293820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966293820&partnerID=8YFLogxK

U2 - 10.1109/WSS.2002.1224368

DO - 10.1109/WSS.2002.1224368

M3 - Conference contribution

AN - SCOPUS:84966293820

T3 - Proceedings of 2002 IEEE Workshop on Speech Synthesis

SP - 39

EP - 42

BT - Proceedings of 2002 IEEE Workshop on Speech Synthesis

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2002 IEEE Workshop on Speech Synthesis

Y2 - 11 September 2002 through 13 September 2002

ER -