Browse > Article
http://dx.doi.org/10.7776/ASK.2007.26.4.159

A Pre-Selection of Candidate Units Using Accentual Characteristic In a Unit Selection Based Japanese TTS System  

Na, Deok-Su (보이스웨어 기술연구소)
Min, So-Yeon (서일대학)
Lee, Kwang-Hyoung (서일대학)
Lee, Jong-Seok (보이스웨어 기술연구소)
Bae, Myung-Jin (숭실대학교 정보통신 전자공학부)
Publication Information
The Journal of the Acoustical Society of Korea / v.26, no.4, 2007 , pp. 159-165 More about this Journal
Abstract
In this paper, we propose a new pre-selection of candidate units that is suitable for the unit selection based Japanese TTS system. General pre-selection method performed by calculating a context-dependent cost within IP (Intonation Phrase). Different from other languages, however. Japanese has an accent represented as the height of a relative pitch, and several words form a single accentual phrase. Also. the prosody in Japanese changes in accentual phrase units. By reflecting such prosodic change in pre-selection. the qualify of synthesized speech can be improved. Furthermore, by calculating a context-dependent cost within accentual phrase, synthesis speed can be improved than calculating within intonation phrase. The proposed method defines AP. analyzes AP in context and performs pre-selection using accentual phrase matching which calculates CCL (connected context length) of the Phoneme's candidates that should be synthesized in each accentual phrase. The baseline system used in the proposed method is VoiceText, which is a synthesizer of Voiceware. Evaluations were made on perceptual error (intonation error, concatenation mismatch error) and synthesis time. Experimental result showed that the proposed method improved the qualify of synthesized speech. as well as shortened the synthesis time.
Keywords
Japanese Speech synthesis; Unit selection; Pre-selection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. Segi, T. Takagi and T. Ito, 'A Concatenative Speech Synthesis Method Using Context Dependent Phoneme Sequences with Variable Length as Search Units', Proc. 5th ISCA Speech Synthesis Workshop, 115-120, Pittsburgh, June, 2004
2 A. Conkie, M. C. Beutnagel, A. K. Svrdal and P. E. Brown, 'Preselection of candidate units in a unit selection-based text-to-speech synthesis system', Proc. ICSLP-2000, 3, 314-317, Beijing, Oct. 2000
3 H. Kawai, T. Toda, J. Ni, M. Tsuzaki, and K. Tokuda: 'Xirnera: A New TTS from ATR Based on Corpus-Based Technologies,' Proc. ISCA 5th Speech Synthesis Workshop, 179-184, Pittsburgh, June, 2004
4 Technical Standardization Committee on Speech Input/Output Systems, 'Speech Synthesis System Performance Evaluation Methods', JEITA IT-4001, 42-45, April. 2003
5 T. Kazuyo, A. Makoto, M. Toshimitsu and I. Shuichi, 'JEIDA Standard of Symbols for Japanese Text-to-Speech Synthesizers', Proc. 3rd Oriental COCOSDA Workshop, 27-32, Beijing, Oct, 2000
6 J. Venditti, 'Japanese ToBI Labeling Guidelines.', OSU Working Papers in Linguistics, 127-162, 1997
7 T. Mizutani and T. Kagosima, 'Concatenative Speech Synthesis Based on the Plural Unit Selection and Fusion Method', IEICE Trans. Inf. & Svst., E88-D, (11) 2565-2572, 2005   DOI