Parsing for prosody: what a text-to-speech system needs from syntax.

E. Fitzpatrick; J. Bachenko

Parsing for prosody: what a text-to-speech system needs from syntax.

E. Fitzpatrick, J. Bachenko

Linguistics

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

6 Scopus citations

Abstract

The authors describe an experimental text-to-speech system that uses a syntactic parser and prosody rules to determine prosodic phrasing for synthesized speech. It is shown that many aspects of sentence analysis that are required for other parsing applications, e.g., machine translation and question answering, become unnecessary in parsing for text-to-speech. It is possible to generate natural-sounding prosodic phrasing by relying on information about syntactic category type, partial constituency, and length; information about clausal and verb phrase constituency, predicate-argument relations, and prepositional phrase attachment can be bypassed.

Original language	English
Title of host publication	Proc Annu AI Syst Gov Conf
Editors	James H. Antonisse, John W. Benoit, Barry G. Silverman
Pages	188-194
Number of pages	7
State	Published - 1 Dec 1989
Event	Proceedings of the Annual AI Systems in Government Conference - Washington, DC, USA Duration: 27 Mar 1989 → 31 Mar 1989

Other

Other	Proceedings of the Annual AI Systems in Government Conference
City	Washington, DC, USA
Period	27/03/89 → 31/03/89

Cite this

@inproceedings{fc0da9b1dfeb48c8bf08a46f17069f38,

title = "Parsing for prosody: what a text-to-speech system needs from syntax.",

abstract = "The authors describe an experimental text-to-speech system that uses a syntactic parser and prosody rules to determine prosodic phrasing for synthesized speech. It is shown that many aspects of sentence analysis that are required for other parsing applications, e.g., machine translation and question answering, become unnecessary in parsing for text-to-speech. It is possible to generate natural-sounding prosodic phrasing by relying on information about syntactic category type, partial constituency, and length; information about clausal and verb phrase constituency, predicate-argument relations, and prepositional phrase attachment can be bypassed.",

author = "E. Fitzpatrick and J. Bachenko",

year = "1989",

month = dec,

day = "1",

language = "English",

isbn = "0818619341",

pages = "188--194",

editor = "Antonisse, {James H.} and Benoit, {John W.} and Silverman, {Barry G.}",

booktitle = "Proc Annu AI Syst Gov Conf",

note = "Proceedings of the Annual AI Systems in Government Conference ; Conference date: 27-03-1989 Through 31-03-1989",

}

TY - GEN

T1 - Parsing for prosody

T2 - Proceedings of the Annual AI Systems in Government Conference

AU - Fitzpatrick, E.

AU - Bachenko, J.

PY - 1989/12/1

Y1 - 1989/12/1

N2 - The authors describe an experimental text-to-speech system that uses a syntactic parser and prosody rules to determine prosodic phrasing for synthesized speech. It is shown that many aspects of sentence analysis that are required for other parsing applications, e.g., machine translation and question answering, become unnecessary in parsing for text-to-speech. It is possible to generate natural-sounding prosodic phrasing by relying on information about syntactic category type, partial constituency, and length; information about clausal and verb phrase constituency, predicate-argument relations, and prepositional phrase attachment can be bypassed.

AB - The authors describe an experimental text-to-speech system that uses a syntactic parser and prosody rules to determine prosodic phrasing for synthesized speech. It is shown that many aspects of sentence analysis that are required for other parsing applications, e.g., machine translation and question answering, become unnecessary in parsing for text-to-speech. It is possible to generate natural-sounding prosodic phrasing by relying on information about syntactic category type, partial constituency, and length; information about clausal and verb phrase constituency, predicate-argument relations, and prepositional phrase attachment can be bypassed.

UR - http://www.scopus.com/inward/record.url?scp=0024866064&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024866064

SN - 0818619341

SP - 188

EP - 194

BT - Proc Annu AI Syst Gov Conf

A2 - Antonisse, James H.

A2 - Benoit, John W.

A2 - Silverman, Barry G.

Y2 - 27 March 1989 through 31 March 1989

ER -

Parsing for prosody: what a text-to-speech system needs from syntax.

Abstract

Other

Other files and links

Fingerprint

Cite this