The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis

Kyoto, Japan
September 22-24, 2010

KLATTSTAT: Knowledge-based Parametric Speech Synthesis

Gopala Krishna Anumanchipalli (1), Ying-Chang Cheng (2),Joseph Fernandez (2), Xiaohan Huang (2), Qi Mao (2), Alan W. Black (1)

(1) Language Technologies Institute; (2) Electrical and Computer Engineering; Carnegie Mellon University, Pittsburgh, PA, USA

This paper is an initial investigation into using knowledge-based parameters in the field of statistical parametric speech synthesis (SPSS). Utilizing the types of speech parameters used in the Klatt Formant Synthesizer we present automatic techniques for deriving such parameters from a speech database and building a statistical parametric speech synthesizer from these derived parameters. Although the work is exploratory, it shows promise in using more speech production inspired parameterizations for statistical speech synthesis.

Index Terms: statistical speech synthesis, Klatt formant synthesizer.

Full Paper

Bibliographic reference.  Anumanchipalli, Gopala Krishna / Cheng, Ying-Chang / Fernandez, oseph / Huang, Xiaohan / Mao, Qi / Black, Alan W. (2010): "KLATTSTAT: knowledge-based parametric speech synthesis", In SSW7-2010, 206-210.