Automatic prosodic segmentation by F 0 clustering using superpositional modeling

Mitsuru Nakai, Harald Singer, Yoshinori Sagisaka, Hiroshi Shimodaira

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, we propose an automatic method for detecting accent phrase boundaries in Japanese continuous speech by using F 0 information. In the training phase, hand labeled accent patterns are parameterized according to a superpositional model proposed by Fujisaki, and assigned to some clusters by a clustering method, in which accent templates are calculated as centroid of each cluster. In the segmentation phase, automatic N-best extraction of boundaries is performed by One-Stage DP matching between the reference templates and the target F 0 contour. About 90% of accent phrase boundaries were correctly detected in speaker independent experiments with the ATR Japanese continuous speech database.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages624-627
Number of pages4
Volume1
Publication statusPublished - 1995
Externally publishedYes
EventProceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 1 (of 5) - Detroit, MI, USA
Duration: 1995 May 91995 May 12

Other

OtherProceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 1 (of 5)
CityDetroit, MI, USA
Period95/5/995/5/12

Fingerprint

templates
centroids
education
Experiments

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Nakai, M., Singer, H., Sagisaka, Y., & Shimodaira, H. (1995). Automatic prosodic segmentation by F 0 clustering using superpositional modeling In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 1, pp. 624-627). IEEE.

Automatic prosodic segmentation by F 0 clustering using superpositional modeling . / Nakai, Mitsuru; Singer, Harald; Sagisaka, Yoshinori; Shimodaira, Hiroshi.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 1 IEEE, 1995. p. 624-627.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakai, M, Singer, H, Sagisaka, Y & Shimodaira, H 1995, Automatic prosodic segmentation by F 0 clustering using superpositional modeling in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 1, IEEE, pp. 624-627, Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 1 (of 5), Detroit, MI, USA, 95/5/9.
Nakai M, Singer H, Sagisaka Y, Shimodaira H. Automatic prosodic segmentation by F 0 clustering using superpositional modeling In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 1. IEEE. 1995. p. 624-627
Nakai, Mitsuru ; Singer, Harald ; Sagisaka, Yoshinori ; Shimodaira, Hiroshi. / Automatic prosodic segmentation by F 0 clustering using superpositional modeling ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 1 IEEE, 1995. pp. 624-627
@inproceedings{54d51160224140a69d772f4bde03bb59,
title = "Automatic prosodic segmentation by F 0 clustering using superpositional modeling",
abstract = "In this paper, we propose an automatic method for detecting accent phrase boundaries in Japanese continuous speech by using F 0 information. In the training phase, hand labeled accent patterns are parameterized according to a superpositional model proposed by Fujisaki, and assigned to some clusters by a clustering method, in which accent templates are calculated as centroid of each cluster. In the segmentation phase, automatic N-best extraction of boundaries is performed by One-Stage DP matching between the reference templates and the target F 0 contour. About 90{\%} of accent phrase boundaries were correctly detected in speaker independent experiments with the ATR Japanese continuous speech database.",
author = "Mitsuru Nakai and Harald Singer and Yoshinori Sagisaka and Hiroshi Shimodaira",
year = "1995",
language = "English",
volume = "1",
pages = "624--627",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Automatic prosodic segmentation by F 0 clustering using superpositional modeling

AU - Nakai, Mitsuru

AU - Singer, Harald

AU - Sagisaka, Yoshinori

AU - Shimodaira, Hiroshi

PY - 1995

Y1 - 1995

N2 - In this paper, we propose an automatic method for detecting accent phrase boundaries in Japanese continuous speech by using F 0 information. In the training phase, hand labeled accent patterns are parameterized according to a superpositional model proposed by Fujisaki, and assigned to some clusters by a clustering method, in which accent templates are calculated as centroid of each cluster. In the segmentation phase, automatic N-best extraction of boundaries is performed by One-Stage DP matching between the reference templates and the target F 0 contour. About 90% of accent phrase boundaries were correctly detected in speaker independent experiments with the ATR Japanese continuous speech database.

AB - In this paper, we propose an automatic method for detecting accent phrase boundaries in Japanese continuous speech by using F 0 information. In the training phase, hand labeled accent patterns are parameterized according to a superpositional model proposed by Fujisaki, and assigned to some clusters by a clustering method, in which accent templates are calculated as centroid of each cluster. In the segmentation phase, automatic N-best extraction of boundaries is performed by One-Stage DP matching between the reference templates and the target F 0 contour. About 90% of accent phrase boundaries were correctly detected in speaker independent experiments with the ATR Japanese continuous speech database.

UR - http://www.scopus.com/inward/record.url?scp=0028996982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028996982&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028996982

VL - 1

SP - 624

EP - 627

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - IEEE

ER -