论文信息 - Creation of speech corpora for the multilingual Bonn Open Synthesis System

Creation of speech corpora for the multilingual Bonn Open Synthesis System

In this paper we present the procedure for creating a new speech corpus for the Bonn Open Synthesis System (BOSS). BOSS has several advantages which make this procedure particularly straightforward and fast. BOSS is open source, allowing flexible use of components and corpora. It shows a clear separation between data and architecture, which means that a change in corpus does not require a change in the architecture. The data formats are strictly defined, making it a very transparent system. The implementation of a small Dutch corpus is used as a case study.

Esther Klabbers | Karlheinz Stöber

[1] Paul Taylor,et al. The architecture of the Festival speech synthesis system , 1998, SSW.

[2] Eam Esther Klabbers,et al. Segmental and prosodic improvements to speech generation , 2000 .

[3] Alan W. Black,et al. Prosody and the Selection of Source Units for Concatenative Synthesis , 1997 .

[4] Wolfgang Wahlster,et al. Verbmobil: Foundations of Speech-to-Speech Translation , 2000, Artificial Intelligence.

[5] Raymond N. J. Veldhuis,et al. Reducing audible spectral discontinuities , 2001, IEEE Trans. Speech Audio Process..

[6] Petra Wagner,et al. Speech synthesis development made easy: the bonn open synthesis system , 2001, INTERSPEECH.

[7] Petra Wagner,et al. Definition of a training set for unit selection-based speech synthesis , 2001, SSW.

[8] Alan W. Black,et al. Limited domain synthesis , 2000, INTERSPEECH.

[9] Esther Klabbers,et al. Predicting segmental durations for Dutch using the sums-of-products approach , 2000, INTERSPEECH.

[10] Petra Wagner,et al. Speech Synthesis Using Multilevel Selection and Concatenation of Units from Large Speech Corpora , 2000 .