Template-driven generation of prosodic information for Chinese concatenative synthesis

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.