Punctuation Annotation using Statistical Prosody Models

Heidi Christensen; Yoshihiko Gotoh; Steve Renals

Punctuation Annotation using Statistical Prosody Models

Heidi Christensen, Yoshihiko Gotoh, Steve Renals

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

Abstract

This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub-4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task.

Original language	English
Title of host publication	Proceedings of the ITRW on Prosody in Speech Recognition and Understanding
Subtitle of host publication	Prosody 2001
Publisher	ISCA
Number of pages	6
Publication status	Published - 2001
Event	ITRW on Prosody in Speech Recognition and Understanding (Prosody 2001) - Molly Pitcher Inn, Red Bank, NJ, United States Duration: 22 Oct 2001 → 24 Oct 2001

Workshop

Workshop	ITRW on Prosody in Speech Recognition and Understanding (Prosody 2001)
Country/Territory	United States
City	Red Bank, NJ
Period	22/10/01 → 24/10/01

Access to Document

pros01-puncSubmitted manuscript, 122 KB

Cite this

@inproceedings{539ecbca03d84cb08e6698ea9f031f02,

title = "Punctuation Annotation using Statistical Prosody Models",

abstract = "This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub-4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task.",

author = "Heidi Christensen and Yoshihiko Gotoh and Steve Renals",

year = "2001",

language = "English",

booktitle = "Proceedings of the ITRW on Prosody in Speech Recognition and Understanding",

publisher = "ISCA",

note = "ITRW on Prosody in Speech Recognition and Understanding (Prosody 2001) ; Conference date: 22-10-2001 Through 24-10-2001",

}

Christensen, H, Gotoh, Y & Renals, S 2001, Punctuation Annotation using Statistical Prosody Models. in Proceedings of the ITRW on Prosody in Speech Recognition and Understanding: Prosody 2001., 6, ISCA, ITRW on Prosody in Speech Recognition and Understanding (Prosody 2001), Red Bank, NJ, United States, 22/10/01. <http://www.isca-speech.org/archive_open/prosody_2001/prsr_006.html>

TY - GEN

T1 - Punctuation Annotation using Statistical Prosody Models

AU - Christensen, Heidi

AU - Gotoh, Yoshihiko

AU - Renals, Steve

PY - 2001

Y1 - 2001

N2 - This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub-4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task.

AB - This paper is about the development of statistical models of prosodic features to generate linguistic meta-data for spoken language. In particular, we are concerned with automatically punctuating the output of a broadcast news speech recogniser. We present a statistical finite state model that combines prosodic, linguistic and punctuation class features. Experimental results are presented using the Hub-4 Broadcast News corpus, and in the light of our results we discuss the issue of a suitable method of evaluating the present task.

M3 - Conference contribution

BT - Proceedings of the ITRW on Prosody in Speech Recognition and Understanding

PB - ISCA

T2 - ITRW on Prosody in Speech Recognition and Understanding (Prosody 2001)

Y2 - 22 October 2001 through 24 October 2001

ER -

Punctuation Annotation using Statistical Prosody Models

Abstract

Workshop

Access to Document

Fingerprint

Cite this