Abstract
This paper describes the AT&T Bell Laboratories Mandarin Chinese concatenative text-to-speech (TTS) system, which is be-ing constructed using the NewTTS architecture for multi-lingual TTS [12]. This Mandarin TTS system is 'corpus-based' in that important components of the system are developed on the basis of the analysis of large text corpora. We concentrate here pri-marily on two modules, namely the word segmentation module and the segmental duration module. We also briefly describe the intonation module and the concatenative unit inventory.
| Original language | English (US) |
|---|---|
| Pages | 1771-1774 |
| Number of pages | 4 |
| State | Published - 1994 |
| Externally published | Yes |
| Event | 3rd International Conference on Spoken Language Processing, ICSLP 1994 - Yokohama, Japan Duration: Sep 18 1994 → Sep 22 1994 |
Conference
| Conference | 3rd International Conference on Spoken Language Processing, ICSLP 1994 |
|---|---|
| Country/Territory | Japan |
| City | Yokohama |
| Period | 9/18/94 → 9/22/94 |
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language