Prosody Generation Model for TTS Systems

ISBN-13: 9783659162770 / Angielski / Miękka / 2012 / 276 str.

Jo O. Paulo Teixeira

Opis

This book presents the development of a prosody system for text-to-speech (TTS) applications. The prosody is responsible for a communicative intention and guarantees some naturalness in the uttered speech. The prosodic features consist in the imposition of the timing, characterized by the segmental durations and pauses, the intonation, characterized by the fundamental frequency (F0) curve, and by the intensity curve. The proposed prosody model consists of several sub-models, namely, the duration model to predict the segmental durations and the model to predict the F0 pattern. The segmental durations model consists of one ANN carefully selected concerning its architecture and type as well as the set of input features with the objective of minimizing the error between predicted and measured durations. One alternative model, is based on same considerations but uses one dedicated ANN for each phoneme. The alternative model, with dedicated ANNs, improved the final performance. The proposed model to predict the F0 contour is based on the Fujisaki model and consists of two sub-models. One predicts the Phrase Commands parameters and the other predicts the Accent Commands parameters.

O autorze

Prof. João P. Teixeira obtained his PhD in Electrical and Computers Engineering at FEUP in 2004 and worked in several projects related with TTS and Prosody. He teaches at the IPB since 1995 mainly in the area of Signal Processing and is author of several scientific publications in journals and conference proceedings about signal processing and ANN.