Modeling and synthesizing emotional speech for catalan text-to-speech synthesis

Ignasi Iriondo; Francesc Alias; Javier Melenchon; M. Angeles Llorca

doi:10.1007/978-3-540-24842-2_20

Modeling and synthesizing emotional speech for catalan text-to-speech synthesis

Ignasi Iriondo, Francesc Alias, Javier Melenchon, M. Angeles Llorca

Producció científica: Capítol de llibre › Contribució a congrés/conferència › Avaluat per experts

9 Cites (Scopus)

Resum

This paper describes an initial approach to emotional speech synthesis in Catalan based on a diphone concatenation TTS system. The main goal of this work is to develop a simple prosodic model for expressive synthesis. This model is obtained from an emotional speech collection artificially generated by means of a copy-prosody experiment. After validating the emotional content of this collection, the model was automated and incorporated into our TTS system. Finally, the automatic speech synthesis system has been evaluated by means of a perceptual test, obtaining encouraging results.

Idioma original	Anglès
Títol de la publicació	Affective Dialogue Systems
Editors	Elisabeth Andre, Laila Dybkjær, Wolfgang Minker, Paul Heisterkamp
Editor	Springer Verlag
Pàgines	197-208
Nombre de pàgines	12
ISBN (imprès)	3540221433, 9783540221432
DOIs	https://doi.org/10.1007/978-3-540-24842-2_20
Estat de la publicació	Publicada - 2004
Publicat externament	Sí
Esdeveniment	Tutorial and Research Workshop on Affective Dialogue Systems, ADS 2004 - Kloster Irsee, Germany Durada: 14 de juny 2004 → 16 de juny 2004

Sèrie de publicacions

Nom	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volum	3068
ISSN (imprès)	0302-9743

Conferència

Conferència	Tutorial and Research Workshop on Affective Dialogue Systems, ADS 2004
País/Territori	Germany
Ciutat	Kloster Irsee
Període	14/06/04 → 16/06/04

Accés al document

10.1007/978-3-540-24842-2_20

Altres arxius i enllaços

Link to publication in Scopus

Com citar-ho

Iriondo, I., Alias, F., Melenchon, J., & Angeles Llorca, M. (2004). Modeling and synthesizing emotional speech for catalan text-to-speech synthesis. In E. Andre, L. Dybkjær, W. Minker, & P. Heisterkamp (Ed.), Affective Dialogue Systems (pàg. 197-208). (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 3068). Springer Verlag. https://doi.org/10.1007/978-3-540-24842-2_20

Iriondo, Ignasi ; Alias, Francesc ; Melenchon, Javier et al. / Modeling and synthesizing emotional speech for catalan text-to-speech synthesis. Affective Dialogue Systems. editor / Elisabeth Andre ; Laila Dybkjær ; Wolfgang Minker ; Paul Heisterkamp. Springer Verlag, 2004. pàg. 197-208 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)).

@inproceedings{0f89e3e8cd954feba76c36eb8cf9d51a,

title = "Modeling and synthesizing emotional speech for catalan text-to-speech synthesis",

abstract = "This paper describes an initial approach to emotional speech synthesis in Catalan based on a diphone concatenation TTS system. The main goal of this work is to develop a simple prosodic model for expressive synthesis. This model is obtained from an emotional speech collection artificially generated by means of a copy-prosody experiment. After validating the emotional content of this collection, the model was automated and incorporated into our TTS system. Finally, the automatic speech synthesis system has been evaluated by means of a perceptual test, obtaining encouraging results.",

author = "Ignasi Iriondo and Francesc Alias and Javier Melenchon and {Angeles Llorca}, M.",

note = "Publisher Copyright: {\textcopyright} 2004 Springer-Verlag Berlin Heidelberg.; Tutorial and Research Workshop on Affective Dialogue Systems, ADS 2004 ; Conference date: 14-06-2004 Through 16-06-2004",

year = "2004",

doi = "10.1007/978-3-540-24842-2_20",

language = "English",

isbn = "3540221433",

series = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

publisher = "Springer Verlag",

pages = "197--208",

editor = "Elisabeth Andre and Laila Dybkj{\ae}r and Wolfgang Minker and Paul Heisterkamp",

booktitle = "Affective Dialogue Systems",

address = "Germany",

}

Iriondo, I , Alias, F, Melenchon, J & Angeles Llorca, M 2004, Modeling and synthesizing emotional speech for catalan text-to-speech synthesis. in E Andre, L Dybkjær, W Minker & P Heisterkamp (ed.), Affective Dialogue Systems. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), vol. 3068, Springer Verlag, pàg. 197-208, Tutorial and Research Workshop on Affective Dialogue Systems, ADS 2004, Kloster Irsee, Germany, 14/06/04. https://doi.org/10.1007/978-3-540-24842-2_20

Modeling and synthesizing emotional speech for catalan text-to-speech synthesis. / Iriondo, Ignasi ; Alias, Francesc; Melenchon, Javier et al.
Affective Dialogue Systems. ed. / Elisabeth Andre; Laila Dybkjær; Wolfgang Minker; Paul Heisterkamp. Springer Verlag, 2004. pàg. 197-208 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 3068).

Producció científica: Capítol de llibre › Contribució a congrés/conferència › Avaluat per experts

TY - GEN

T1 - Modeling and synthesizing emotional speech for catalan text-to-speech synthesis

AU - Iriondo, Ignasi

AU - Alias, Francesc

AU - Melenchon, Javier

AU - Angeles Llorca, M.

PY - 2004

Y1 - 2004

N2 - This paper describes an initial approach to emotional speech synthesis in Catalan based on a diphone concatenation TTS system. The main goal of this work is to develop a simple prosodic model for expressive synthesis. This model is obtained from an emotional speech collection artificially generated by means of a copy-prosody experiment. After validating the emotional content of this collection, the model was automated and incorporated into our TTS system. Finally, the automatic speech synthesis system has been evaluated by means of a perceptual test, obtaining encouraging results.

AB - This paper describes an initial approach to emotional speech synthesis in Catalan based on a diphone concatenation TTS system. The main goal of this work is to develop a simple prosodic model for expressive synthesis. This model is obtained from an emotional speech collection artificially generated by means of a copy-prosody experiment. After validating the emotional content of this collection, the model was automated and incorporated into our TTS system. Finally, the automatic speech synthesis system has been evaluated by means of a perceptual test, obtaining encouraging results.

UR - http://www.scopus.com/inward/record.url?scp=9444255201&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-24842-2_20

DO - 10.1007/978-3-540-24842-2_20

M3 - Conference contribution

AN - SCOPUS:9444255201

SN - 3540221433

SN - 9783540221432

T3 - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

SP - 197

EP - 208

BT - Affective Dialogue Systems

A2 - Andre, Elisabeth

A2 - Dybkjær, Laila

A2 - Minker, Wolfgang

A2 - Heisterkamp, Paul

PB - Springer Verlag

T2 - Tutorial and Research Workshop on Affective Dialogue Systems, ADS 2004

Y2 - 14 June 2004 through 16 June 2004

ER -

Iriondo I , Alias F, Melenchon J, Angeles Llorca M. Modeling and synthesizing emotional speech for catalan text-to-speech synthesis. In Andre E, Dybkjær L, Minker W, Heisterkamp P, editors, Affective Dialogue Systems. Springer Verlag. 2004. pàg. 197-208. (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)). doi: 10.1007/978-3-540-24842-2_20

Modeling and synthesizing emotional speech for catalan text-to-speech synthesis

Resum

Sèrie de publicacions

Conferència

Accés al document

Altres arxius i enllaços

Fingerprint

Com citar-ho