DocumentCode :
394240
Title :
Towards spontaneous speech synthesis - LM based selection of pronunciation variants
Author :
Eichner, Matthias ; Werner, Steffen ; Wolff, Matthias ; Hoffmann, Rudiger
Author_Institution :
Lab. of Acoust. & Speech Commun., Dresden Univ. of Technol., Germany
Volume :
1
fYear :
2003
fDate :
6-10 April 2003
Abstract :
State of the art speech synthesis systems achieve a high overall quality. However, the synthesized speech still lacks naturalness. To make speech synthesis more natural and colloquial we are trying to integrate effects that are observable in spontaneous speech. In a previous paper we introduced a new approach for duration control in speech synthesis that uses the probability of a word in its context to control the local speaking rate within the utterance. This idea is based on the observation that words that are very likely to occur in a given context are pronounced faster than improbable ones. Since probable words are not only pronounced faster but also less accurate we extend this approach by selecting appropriate pronunciation variants to realize the change in the local speaking rate.
Keywords :
grammars; speech intelligibility; speech synthesis; LM based pronunciation variants selection; colloquial speech; databases; duration control; improbable words; local speaking rate; local speaking rate control; n-gram language model; probability; probable words; speech naturalness; speech quality; speech recognition; speech synthesis systems; spontaneous speech synthesis; variant lexicon; Acoustics; Control system synthesis; Databases; Laboratories; Natural languages; Oral communication; Speech recognition; Speech synthesis; Synthesizers; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-7663-3
Type :
conf
DOI :
10.1109/ICASSP.2003.1198764
Filename :
1198764
Link To Document :
بازگشت