Template-driven generation of prosodic information for Chinese concatenative synthesis

Authors:
Chung-Hsien Hu;Jau-Hung Chen
Affiliations:
Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan;-
Venue:
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Year:
1999

Citing 0
Cited 2

Learning Prosodic Patterns for Mandarin Speech Synthesis

Journal of Intelligent Information Systems
Speech act modeling in a spoken dialog system using a fuzzy fragment-class Markov model

Speech Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

A template-driven generation of prosodic information is proposed for Chinese text-to-speech conversion. A set of monosyllable-based synthesis units is selected from a large continuous speech database. The speech database is employed to establish a word-prosody-based template tree according to the linguistic features: tone combination, word length, part-of-speech (POS) of the word, and word position in a sentence. This template tree stores the prosodic features including pitch contour, average energy, and syllable duration of a word for possible combinations of linguistic features. Two modules for sentence intonation and template selection are proposed to generate the target prosodic templates. The experimental results for the TTS conversion system showed that synthesized prosodic features quite resembled their original counterparts for most syllables in the inside test. Evaluation by subjective experiments also confirmed the satisfactory performance of these approaches.