Paper: The Contribution Of Parsing To Prosodic Phrasing In An Experimental Text-To-Speech System

Webmaster's Note: The whole dataset is available Here. Please download the dataset instead of crawling the website.

Basic Info:

id: P86-1022
title: The Contribution Of Parsing To Prosodic Phrasing In An Experimental Text-To-Speech System
authors: Bachenko, Joan (AT&T Bell Labs, Murray Hill NJ), Fitzpatrick, Eileen (AT&T Bell Labs, Murray Hill NJ), Wright, C. E. (AT&T Bell Labs, Murray Hill NJ)
venue: ACL
year: 1986
pdf: link

Abstract

While various aspects of syntactic structure have been shown to bear on the determination of phrase- level 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.

Statistics Summary
Stat	Rank	Value
Incoming Citations	2706(2621)	4(3)
Outgoing Citations	10583(9875)	0(0)
PageRank	5	7969
PageRank per Year	7	362.22

Incoming Citations
Id	Title
A88-1030	Finding Clauses In Unrestricted Text By Finitary And Stochastic Methods
J89-2002	Parsing With A Small Dictionary For Applications Such As Text To Speech
J90-3003	A Computational Grammar Of Discourse-Neutral Prosodic Phrasing In English
C94-2160	The Parsody System: Automatic Prediction Of Prosodic Boundaries For Text-To-Speech

Outgoing Citations
Id	Title
None	No Outgoing Citations

Top Similar Papers
By Title

ID	Title
C82-1019	An Experimental Parser
C88-1063	An Experimental Parser For Systemic Grammars
C90-2024	Contribution Of A Category Hierarchy To The Robustness Of Syntactic Parsing
J90-3003	A Computational Grammar Of Discourse-Neutral Prosodic Phrasing In English
C88-2139	Linguistic Contributions To Text-To-Speech Computer Programs For French
C80-1035	Topic-Comment Structure Of Texts (And Its Contribution To The Automatic Processing Of Texts)
H92-1087	Probabilistic Parse Scoring Based On Prosodic Phrasing
C88-1041	The PSI/PHI Architecture For Prosodic Parsing
E87-1038	Coping With Dynamic Syntactic Strategies: An Experimental Environment For An Experimental Parser
L08-1374	An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation

By Abstract

ID	Title
H93-1063	Session 11: Prosody
H92-1084	Session 13: Prosody
W97-1202	Message-To-Speech: High Quality Speech Generation For Messaging And Dialogue Systems
W00-0716	Generating Synthetic Speech Prosody With Lazy Learning In Tree Structures
H89-2002	Prosody And Parsing
H93-1064	On Customizing Prosody In Speech Synthesis: Names And Addresses As A Case In Point
P92-1015	Prosodic Aids To Syntactic And Semantic Analysis Of Spoken English
W97-1208	Looking For The Presence Of Linguistic Concepts In The Prosody Of Spoken Utterances
W97-1203	A Compact Representation Of Prosodically Relevant Knowledge In A Speech Dialogue System
A88-1016	The MULTIVOC Text-To-Speech System

By Full Text

ID	Title
J90-3003	A Computational Grammar Of Discourse-Neutral Prosodic Phrasing In English
P90-1003	Prosody Syntax And Parsing
W97-1206	Computing Prosodic Properties In A Data-To-Speech System
P85-1023	Analysis Of Conjunctions In A Rule-Based Parser
C96-1014	Integrating Syntactic And Prosodic Information For The Efficient Detection Of Empty Categories
H90-1028	Preliminary ATIS Development At MIT
J95-1004	An Automatic Procedure For Topic-Focus Identification
A92-1026	Robust Processing Of Real-World Natural-Language Texts
J89-3002	Knowledge Representation For Commonsense Reasoning With Text
M98-1005	University Of Durham: Description Of The LOLITA System As Used In MUC-7

By Co-citation

ID	Title	Num Co-citations
A88-1019	A Stochastic Parts Program And Noun Phrase Parser For Unrestricted Text	3
A88-1016	The MULTIVOC Text-To-Speech System	1
P87-1020	Toward Treating English Nominals Correctly	1
J90-3003	A Computational Grammar Of Discourse-Neutral Prosodic Phrasing In English	1
J89-2002	Parsing With A Small Dictionary For Applications Such As Text To Speech	1
J86-1001	Resolving Lexical Ambiguity In A Deterministic Parser	1
J83-3002	Parse Fitting And Prose Fixing: Getting A Hold On Ill-Formedness	1
J80-2003	Responding Intelligently To Unparsable Inputs	1
H91-1075	Use Of Prosody In Syntactic Disambiguation: An Analysis-By-Synthesis Approach	1
H91-1074	Predicting Intonational Boundaries Automatically From Text: The ATIS Domain	1

Citation Summary
Citing sentences
J90-3003 1 6:623 1 INTRODUCTION In previous work (Bachenko et al. 1986), we described an experimental text-to-speech system that determined prosodic phrasing for the Olive-Liberman synthesizer (Olive and Liberman 1985).