HMM-based Speech Synthesis with an Acoustic Glottal Source Model

Javier Cabral; Steve Renals; Korin Richmond; Junichi Yamagishi

HMM-based Speech Synthesis with an Acoustic Glottal Source Model

Javier Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A major cause of degradation of speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.

Original language	English
Title of host publication	Proc. The First Young Researchers Workshop in Speech Technology
Publication status	Published - 2009

Access to Document

HMM-based Speech Synthesis with an Acoustic Glottal Source ModelAccepted author manuscript, 22.3 KB

Cite this

@inproceedings{5d4246c0840045eb8279d888322f2ae8,

title = "HMM-based Speech Synthesis with an Acoustic Glottal Source Model",

abstract = "A major cause of degradation of speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.",

author = "Javier Cabral and Steve Renals and Korin Richmond and Junichi Yamagishi",

year = "2009",

language = "English",

booktitle = "Proc. The First Young Researchers Workshop in Speech Technology",

}

TY - GEN

T1 - HMM-based Speech Synthesis with an Acoustic Glottal Source Model

AU - Cabral, Javier

AU - Renals, Steve

AU - Richmond, Korin

AU - Yamagishi, Junichi

PY - 2009

Y1 - 2009

N2 - A major cause of degradation of speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.

AB - A major cause of degradation of speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.

M3 - Conference contribution

BT - Proc. The First Young Researchers Workshop in Speech Technology

ER -

HMM-based Speech Synthesis with an Acoustic Glottal Source Model

Abstract

Access to Document

Fingerprint

Cite this