Estimating speaker-specific intonation patterns using the linear alignment model

Géza Kiss, Jan Van Santen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Modeling speaker-specific intonation is important in several areas, including speaker identification, verification, and imitation using text-to-speech synthesis. However the choice of the intonation model and the estimation of its parameters from spontaneous speech remains a challenge. We propose a way to estimate speaker-specific intonation parameters for a particular superpositional model, the Simplified Linear Alignment Model [1], using robust per-utterance and overall statistics of spontaneous speech. We used this method to compare the intonation of children with autism or language impairment, who often have atypical speech prosody, with that of typically developing children. We found significant differences between the groups, which demonstrates the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
PublisherInternational Speech and Communication Association
Pages354-358
Number of pages5
StatePublished - 2013
Event14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France
Duration: Aug 25 2013Aug 29 2013

Other

Other14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013
CountryFrance
CityLyon
Period8/25/138/29/13

Fingerprint

Alignment
Speaker Identification
Text-to-speech
Prosody
Speech Synthesis
Speech synthesis
Imitation
Statistics
Model
Modeling
Estimate
Demonstrate
Speech
Intonation
Children
Spontaneous Speech
Language

Keywords

  • Autism
  • Estimating speakerspecific intonation
  • Language impairment
  • Linear alignment model

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Cite this

Kiss, G., & Van Santen, J. (2013). Estimating speaker-specific intonation patterns using the linear alignment model. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 354-358). International Speech and Communication Association.

Estimating speaker-specific intonation patterns using the linear alignment model. / Kiss, Géza; Van Santen, Jan.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. International Speech and Communication Association, 2013. p. 354-358.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kiss, G & Van Santen, J 2013, Estimating speaker-specific intonation patterns using the linear alignment model. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. International Speech and Communication Association, pp. 354-358, 14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013, Lyon, France, 8/25/13.
Kiss G, Van Santen J. Estimating speaker-specific intonation patterns using the linear alignment model. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. International Speech and Communication Association. 2013. p. 354-358
Kiss, Géza ; Van Santen, Jan. / Estimating speaker-specific intonation patterns using the linear alignment model. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. International Speech and Communication Association, 2013. pp. 354-358
@inproceedings{612a1d1b25864ed898717927c1c3bc06,
title = "Estimating speaker-specific intonation patterns using the linear alignment model",
abstract = "Modeling speaker-specific intonation is important in several areas, including speaker identification, verification, and imitation using text-to-speech synthesis. However the choice of the intonation model and the estimation of its parameters from spontaneous speech remains a challenge. We propose a way to estimate speaker-specific intonation parameters for a particular superpositional model, the Simplified Linear Alignment Model [1], using robust per-utterance and overall statistics of spontaneous speech. We used this method to compare the intonation of children with autism or language impairment, who often have atypical speech prosody, with that of typically developing children. We found significant differences between the groups, which demonstrates the effectiveness of the proposed method.",
keywords = "Autism, Estimating speakerspecific intonation, Language impairment, Linear alignment model",
author = "G{\'e}za Kiss and {Van Santen}, Jan",
year = "2013",
language = "English (US)",
pages = "354--358",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech and Communication Association",

}

TY - GEN

T1 - Estimating speaker-specific intonation patterns using the linear alignment model

AU - Kiss, Géza

AU - Van Santen, Jan

PY - 2013

Y1 - 2013

N2 - Modeling speaker-specific intonation is important in several areas, including speaker identification, verification, and imitation using text-to-speech synthesis. However the choice of the intonation model and the estimation of its parameters from spontaneous speech remains a challenge. We propose a way to estimate speaker-specific intonation parameters for a particular superpositional model, the Simplified Linear Alignment Model [1], using robust per-utterance and overall statistics of spontaneous speech. We used this method to compare the intonation of children with autism or language impairment, who often have atypical speech prosody, with that of typically developing children. We found significant differences between the groups, which demonstrates the effectiveness of the proposed method.

AB - Modeling speaker-specific intonation is important in several areas, including speaker identification, verification, and imitation using text-to-speech synthesis. However the choice of the intonation model and the estimation of its parameters from spontaneous speech remains a challenge. We propose a way to estimate speaker-specific intonation parameters for a particular superpositional model, the Simplified Linear Alignment Model [1], using robust per-utterance and overall statistics of spontaneous speech. We used this method to compare the intonation of children with autism or language impairment, who often have atypical speech prosody, with that of typically developing children. We found significant differences between the groups, which demonstrates the effectiveness of the proposed method.

KW - Autism

KW - Estimating speakerspecific intonation

KW - Language impairment

KW - Linear alignment model

UR - http://www.scopus.com/inward/record.url?scp=84906238907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906238907&partnerID=8YFLogxK

M3 - Conference contribution

SP - 354

EP - 358

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

PB - International Speech and Communication Association

ER -