Speaking style dependency of formant targets

Akiko Amano-Kusumoto; John Paul Hosom; Alexander Kain

Speaking style dependency of formant targets

Akiko Amano-Kusumoto, John Paul Hosom, Alexander Kain

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

Abstract

Previous work on formant targets has assumed that these targets are independent of the speaking style. In this paper, we estimate consonant and vowel targets in a database of "clear" and "conversational" speech, using both style-independent and style-dependent models. The test-set errors and clustering of the estimated target values indicate that for this corpus, formant targets depend on the speaking style. Vowel classification accuracy was then tested on estimated target values and compared with classification based on observed formant values. Token-based style-independent classification shows greater accuracy for conversational speech (82.19%) than observed-value classification (73.97%).

Original language	English (US)
Title of host publication	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Publisher	International Speech Communication Association
Pages	905-908
Number of pages	4
State	Published - 2010
Externally published	Yes

Publication series

Name	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Keywords

Clear speech
Formant contour model
Formant target

ASJC Scopus subject areas

Language and Linguistics
Speech and Hearing

Cite this

Amano-Kusumoto, A., Hosom, J. P., & Kain, A. (2010). Speaking style dependency of formant targets. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 905-908). (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010). International Speech Communication Association.

Speaking style dependency of formant targets. / Amano-Kusumoto, Akiko; Hosom, John Paul; Kain, Alexander.

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. p. 905-908 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

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

Amano-Kusumoto, A, Hosom, JP & Kain, A 2010, Speaking style dependency of formant targets. in Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, International Speech Communication Association, pp. 905-908.

Amano-Kusumoto A, Hosom JP, Kain A. Speaking style dependency of formant targets. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association. 2010. p. 905-908. (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

Amano-Kusumoto, Akiko ; Hosom, John Paul ; Kain, Alexander. / Speaking style dependency of formant targets. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. pp. 905-908 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

@inproceedings{04aedf6f47824af6919d4eb1a8e88bdf,

title = "Speaking style dependency of formant targets",

abstract = "Previous work on formant targets has assumed that these targets are independent of the speaking style. In this paper, we estimate consonant and vowel targets in a database of {"}clear{"} and {"}conversational{"} speech, using both style-independent and style-dependent models. The test-set errors and clustering of the estimated target values indicate that for this corpus, formant targets depend on the speaking style. Vowel classification accuracy was then tested on estimated target values and compared with classification based on observed formant values. Token-based style-independent classification shows greater accuracy for conversational speech (82.19%) than observed-value classification (73.97%).",

keywords = "Clear speech, Formant contour model, Formant target",

author = "Akiko Amano-Kusumoto and Hosom, {John Paul} and Alexander Kain",

year = "2010",

language = "English (US)",

series = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

publisher = "International Speech Communication Association",

pages = "905--908",

booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

}

TY - GEN

T1 - Speaking style dependency of formant targets

AU - Amano-Kusumoto, Akiko

AU - Hosom, John Paul

AU - Kain, Alexander

PY - 2010

Y1 - 2010

N2 - Previous work on formant targets has assumed that these targets are independent of the speaking style. In this paper, we estimate consonant and vowel targets in a database of "clear" and "conversational" speech, using both style-independent and style-dependent models. The test-set errors and clustering of the estimated target values indicate that for this corpus, formant targets depend on the speaking style. Vowel classification accuracy was then tested on estimated target values and compared with classification based on observed formant values. Token-based style-independent classification shows greater accuracy for conversational speech (82.19%) than observed-value classification (73.97%).

AB - Previous work on formant targets has assumed that these targets are independent of the speaking style. In this paper, we estimate consonant and vowel targets in a database of "clear" and "conversational" speech, using both style-independent and style-dependent models. The test-set errors and clustering of the estimated target values indicate that for this corpus, formant targets depend on the speaking style. Vowel classification accuracy was then tested on estimated target values and compared with classification based on observed formant values. Token-based style-independent classification shows greater accuracy for conversational speech (82.19%) than observed-value classification (73.97%).

KW - Clear speech

KW - Formant contour model

KW - Formant target

UR - http://www.scopus.com/inward/record.url?scp=79959815303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959815303&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79959815303

T3 - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

SP - 905

EP - 908

BT - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

PB - International Speech Communication Association

ER -

Speaking style dependency of formant targets

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this