Integrating phrasing and intonation modelling using syntactic and morphosyntactic information

Francisco Campillo Díaz; Jan van Santen; Eduardo Rodríguez Banga

doi:10.1016/j.specom.2009.01.007

Integrating phrasing and intonation modelling using syntactic and morphosyntactic information

Francisco Campillo Díaz
, Jan van Santen
, Eduardo Rodríguez Banga

Institute on Development and Disability

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5% of sentences were rated as worse or much worse.

Original language	English (US)
Pages (from-to)	452-465
Number of pages	14
Journal	Speech Communication
Volume	51
Issue number	5
DOIs	https://doi.org/10.1016/j.specom.2009.01.007
State	Published - May 1 2009

Funding

The work reported here was carried out while the first author was a visiting post-doctoral researcher at the Center for Spoken Language Understanding, with funding from the Xunta de Galicia “Isidro Parga Pondal” research programme and PGIDIT05TIC32202-PR programme, and with support from NSF Grant 0205731, “ITR: Prosody Generation for Child Oriented Speech Synthesis” (PI Jan van Santen), and MEC under the Project TEC2006-13694-C03-03. Thanks also to Paul Hosom and Raychel Moldover, for their comments and suggestions on the paper.

Funders	Funder number
Center for Spoken Language Understanding
Author National Science Foundation National Science Foundation National Institutes of Health National Institutes of Health National Institutes of Health National Institutes of Health National Science Foundation National Science Foundation
Directorate for Computer and Information Science and Engineering	0205731
Ministerio de Economía y Competitividad	TEC2006-13694-C03-03
Consellería de Cultura, Educación e Ordenación Universitaria, Xunta de Galicia	PGIDIT05TIC32202-PR

Keywords

Corpus-based
Intonation modelling
POS
Phrasing
Syntax
Unit selection

ASJC Scopus subject areas

Software
Modeling and Simulation
Communication
Language and Linguistics
Linguistics and Language
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1016/j.specom.2009.01.007

Cite this

@article{89e367da780a4f7b9f22503313ffaca1,

title = "Integrating phrasing and intonation modelling using syntactic and morphosyntactic information",

abstract = "This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75\% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5\% of sentences were rated as worse or much worse.",

keywords = "Corpus-based, Intonation modelling, POS, Phrasing, Syntax, Unit selection",

author = "D{\'i}az, \{Francisco Campillo\} and \{van Santen\}, Jan and Banga, \{Eduardo Rodr{\'i}guez\}",

note = "Funding Information: The work reported here was carried out while the first author was a visiting post-doctoral researcher at the Center for Spoken Language Understanding, with funding from the Xunta de Galicia {\textquotedblleft}Isidro Parga Pondal{\textquotedblright} research programme and PGIDIT05TIC32202-PR programme, and with support from NSF Grant 0205731, {\textquotedblleft}ITR: Prosody Generation for Child Oriented Speech Synthesis{\textquotedblright} (PI Jan van Santen), and MEC under the Project TEC2006-13694-C03-03. Thanks also to Paul Hosom and Raychel Moldover, for their comments and suggestions on the paper.",

year = "2009",

month = may,

day = "1",

doi = "10.1016/j.specom.2009.01.007",

language = "English (US)",

volume = "51",

pages = "452--465",

journal = "Speech Communication",

issn = "0167-6393",

publisher = "Elsevier B.V.",

number = "5",

}

TY - JOUR

T1 - Integrating phrasing and intonation modelling using syntactic and morphosyntactic information

AU - Díaz, Francisco Campillo

AU - van Santen, Jan

AU - Banga, Eduardo Rodríguez

N1 - Funding Information: The work reported here was carried out while the first author was a visiting post-doctoral researcher at the Center for Spoken Language Understanding, with funding from the Xunta de Galicia “Isidro Parga Pondal” research programme and PGIDIT05TIC32202-PR programme, and with support from NSF Grant 0205731, “ITR: Prosody Generation for Child Oriented Speech Synthesis” (PI Jan van Santen), and MEC under the Project TEC2006-13694-C03-03. Thanks also to Paul Hosom and Raychel Moldover, for their comments and suggestions on the paper.

PY - 2009/5/1

Y1 - 2009/5/1

N2 - This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5% of sentences were rated as worse or much worse.

AB - This paper focuses on the relationship between intonation and syntactic and morphosyntactic information. Although intonation and syntax are both related to dependencies between the different parts of a sentence, and are therefore related to meaning, the precise influence of grammar on intonation is not clear. We describe a novel method that uses syntactic and part-of-speech features in the framework of corpus-based intonation modelling, and which integrates part of the phrasing algorithm in the unit selection stage. Subjective tests confirm an improvement in the quality of the resulting synthetic intonation: 75% of the sentences synthesised with the new intonation model were considered to be better or much better than the sentences synthesised using the old model, while only 7.5% of sentences were rated as worse or much worse.

KW - Corpus-based

KW - Intonation modelling

KW - POS

KW - Phrasing

KW - Syntax

KW - Unit selection

UR - https://www.scopus.com/pages/publications/61749092962

UR - https://www.scopus.com/pages/publications/61749092962#tab=citedBy

U2 - 10.1016/j.specom.2009.01.007

DO - 10.1016/j.specom.2009.01.007

M3 - Article

AN - SCOPUS:61749092962

SN - 0167-6393

VL - 51

SP - 452

EP - 465

JO - Speech Communication

JF - Speech Communication

IS - 5

ER -

Integrating phrasing and intonation modelling using syntactic and morphosyntactic information

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this