Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

Yi Fen Liu; Shu Chuan Tseng; J. S.Roger Jang; C. H.Alvin Chen

Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

Yi Fen Liu^*, Shu Chuan Tseng, J. S.Roger Jang, C. H.Alvin Chen

^*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.

Original language	English
Title of host publication	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Publisher	International Speech Communication Association
Pages	1417-1420
Number of pages	4
Publication status	Published - 2010
Externally published	Yes

Publication series

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

Keywords

Biased minimax probability machine
Machine learning
Prosodic unit

ASJC Scopus subject areas

Language and Linguistics
Speech and Hearing
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

Liu, Y. F., Tseng, S. C., Jang, J. S. R., & Chen, C. H. A. (2010). Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 1417-1420). (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010). International Speech Communication Association.

Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features. / Liu, Yi Fen; Tseng, Shu Chuan; Jang, J. S.Roger et al.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. p. 1417-1420 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

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

Liu, YF, Tseng, SC, Jang, JSR & Chen, CHA 2010, Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features. 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. 1417-1420.

Liu YF, Tseng SC, Jang JSR, Chen CHA. Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association. 2010. p. 1417-1420. (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

Liu, Yi Fen ; Tseng, Shu Chuan ; Jang, J. S.Roger et al. / Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. pp. 1417-1420 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

@inproceedings{fe81207341f14137b9fde44e5dc9fdb4,

title = "Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features",

abstract = "Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.",

keywords = "Biased minimax probability machine, Machine learning, Prosodic unit",

author = "Liu, {Yi Fen} and Tseng, {Shu Chuan} and Jang, {J. S.Roger} and Chen, {C. H.Alvin}",

note = "Funding Information: This work was supported by the Computational Linguistics and Chinese Language Processing Program, Academia Sinica, Taiwan.",

year = "2010",

language = "English",

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

publisher = "International Speech Communication Association",

pages = "1417--1420",

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

}

TY - GEN

T1 - Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

AU - Liu, Yi Fen

AU - Tseng, Shu Chuan

AU - Jang, J. S.Roger

AU - Chen, C. H.Alvin

N1 - Funding Information: This work was supported by the Computational Linguistics and Chinese Language Processing Program, Academia Sinica, Taiwan.

PY - 2010

Y1 - 2010

N2 - Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.

AB - Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.

KW - Biased minimax probability machine

KW - Machine learning

KW - Prosodic unit

UR - http://www.scopus.com/inward/record.url?scp=79959815052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959815052&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79959815052

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

SP - 1417

EP - 1420

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

PB - International Speech Communication Association

ER -

Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this