A hybrid method oriented to concatenative text-to-speech synthesis

Ignasi Iriondo; Francesc Alías; Javier Sanchis; Javier Melenchón

A hybrid method oriented to concatenative text-to-speech synthesis

Ignasi Iriondo, Francesc Alías, Javier Sanchis, Javier Melenchón

Producció científica: Contribució a una conferència › Contribució › Avaluat per experts

3 Cites (Scopus)

Resum

In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.

Idioma original	Anglès
Pàgines	2953-2956
Nombre de pàgines	4
Estat de la publicació	Publicada - 2003
Esdeveniment	8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - Geneva, Switzerland Durada: 1 de set. 2003 → 4 de set. 2003

Conferència

Conferència	8th European Conference on Speech Communication and Technology, EUROSPEECH 2003
País/Territori	Switzerland
Ciutat	Geneva
Període	1/09/03 → 4/09/03

Altres arxius i enllaços

Link to publication in Scopus

Com citar-ho

@conference{4aba99673e17471f84738780b95f61bd,

title = "A hybrid method oriented to concatenative text-to-speech synthesis",

abstract = "In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.",

author = "Ignasi Iriondo and Francesc Al{\'i}as and Javier Sanchis and Javier Melench{\'o}n",

year = "2003",

language = "English",

pages = "2953--2956",

note = "8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 ; Conference date: 01-09-2003 Through 04-09-2003",

}

TY - CONF

T1 - A hybrid method oriented to concatenative text-to-speech synthesis

AU - Iriondo, Ignasi

AU - Alías, Francesc

AU - Sanchis, Javier

AU - Melenchón, Javier

PY - 2003

Y1 - 2003

N2 - In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.

AB - In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.

UR - https://www.scopus.com/pages/publications/85009168088

M3 - Contribution

AN - SCOPUS:85009168088

SP - 2953

EP - 2956

T2 - 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003

Y2 - 1 September 2003 through 4 September 2003

ER -

A hybrid method oriented to concatenative text-to-speech synthesis

Resum

Conferència

Altres arxius i enllaços

Fingerprint

Com citar-ho