The contribution of parsing to prosodic phrasing in an experimental text-to-speech system

Joan Bachenko; Eileen Fitzpatrick; C. E. Wright

The contribution of parsing to prosodic phrasing in an experimental text-to-speech system

Joan Bachenko, Eileen Fitzpatrick, C. E. Wright

Linguistics

Research output: Contribution to journal › Conference article › peer-review

Abstract

While various aspects of syntactic structure have been shown to bear on the determination of phraselevel prosody, the text-to-speech field has lacked a robust working system to test the possible relations between syntax and prosody. We describe an implemented system which uses the deterministic parser Fidditch to create the input for a set of prosody rules. The prosody rules generate a prosody tree that specifies the location and relative strength of prosodic phrase boundaries. These specifications are converted to annotations for the Bell Labs text-to-speech system that dictate modulations in pitch and duration for the input sentence. We discuss the results of an experiment to determine the performance of our system. We are encouraged by an initial 5 percent error rate and we see the design of the parser and the modularity of the system allowing changes that will upgrade this rate.

Original language	English
Pages (from-to)	145-155
Number of pages	11
Journal	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	1986-July
State	Published - 1986
Event	24th Annual Meeting of the Association for Computational Linguistics, ACL 1986 - New York, United States Duration: 10 Jul 1986 → 13 Jul 1986

Cite this

@article{2a5d48a89ad64915ab6eac22335d6fac,

title = "The contribution of parsing to prosodic phrasing in an experimental text-to-speech system",

abstract = "While various aspects of syntactic structure have been shown to bear on the determination of phraselevel prosody, the text-to-speech field has lacked a robust working system to test the possible relations between syntax and prosody. We describe an implemented system which uses the deterministic parser Fidditch to create the input for a set of prosody rules. The prosody rules generate a prosody tree that specifies the location and relative strength of prosodic phrase boundaries. These specifications are converted to annotations for the Bell Labs text-to-speech system that dictate modulations in pitch and duration for the input sentence. We discuss the results of an experiment to determine the performance of our system. We are encouraged by an initial 5 percent error rate and we see the design of the parser and the modularity of the system allowing changes that will upgrade this rate.",

author = "Joan Bachenko and Eileen Fitzpatrick and Wright, {C. E.}",

note = "Publisher Copyright: {\textcopyright} 1986 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All Rights Reserved.; 24th Annual Meeting of the Association for Computational Linguistics, ACL 1986 ; Conference date: 10-07-1986 Through 13-07-1986",

year = "1986",

language = "English",

volume = "1986-July",

pages = "145--155",

journal = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

issn = "0736-587X",

}

TY - JOUR

T1 - The contribution of parsing to prosodic phrasing in an experimental text-to-speech system

AU - Bachenko, Joan

AU - Fitzpatrick, Eileen

AU - Wright, C. E.

PY - 1986

Y1 - 1986

N2 - While various aspects of syntactic structure have been shown to bear on the determination of phraselevel prosody, the text-to-speech field has lacked a robust working system to test the possible relations between syntax and prosody. We describe an implemented system which uses the deterministic parser Fidditch to create the input for a set of prosody rules. The prosody rules generate a prosody tree that specifies the location and relative strength of prosodic phrase boundaries. These specifications are converted to annotations for the Bell Labs text-to-speech system that dictate modulations in pitch and duration for the input sentence. We discuss the results of an experiment to determine the performance of our system. We are encouraged by an initial 5 percent error rate and we see the design of the parser and the modularity of the system allowing changes that will upgrade this rate.

AB - While various aspects of syntactic structure have been shown to bear on the determination of phraselevel prosody, the text-to-speech field has lacked a robust working system to test the possible relations between syntax and prosody. We describe an implemented system which uses the deterministic parser Fidditch to create the input for a set of prosody rules. The prosody rules generate a prosody tree that specifies the location and relative strength of prosodic phrase boundaries. These specifications are converted to annotations for the Bell Labs text-to-speech system that dictate modulations in pitch and duration for the input sentence. We discuss the results of an experiment to determine the performance of our system. We are encouraged by an initial 5 percent error rate and we see the design of the parser and the modularity of the system allowing changes that will upgrade this rate.

UR - http://www.scopus.com/inward/record.url?scp=84977295543&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84977295543

SN - 0736-587X

VL - 1986-July

SP - 145

EP - 155

JO - Proceedings of the Annual Meeting of the Association for Computational Linguistics

JF - Proceedings of the Annual Meeting of the Association for Computational Linguistics

T2 - 24th Annual Meeting of the Association for Computational Linguistics, ACL 1986

Y2 - 10 July 1986 through 13 July 1986

ER -

The contribution of parsing to prosodic phrasing in an experimental text-to-speech system

Abstract

Other files and links

Fingerprint

Cite this