Utilization of an HMM-Based Feature Generation Module in 5 ms Segment Concatenative Speech Synthesis

6th ISCA Workshop on Speech Synthesis, SSW 2007

Volumn , Issue , 2007, Pages 81-84

  Hirai, Toshio ^a   Yamagishi, Junichi ^b   Tenpaku, Seiichi ^a  

^a Arcadia Inc ^*  (Japan)

^b UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

CONCATENATIVE SPEECH SYNTHESIS; CONCATENATIVE SPEECH SYNTHESIS SYSTEMS; FEATURE GENERATION; HMM-BASED; NATURAL SPEECH; SHORTEST SEGMENT; SPEECH SEGMENTS; SYNTHESIS EXPERIMENT; SYSTEM USE;

SPEECH SYNTHESIS;

EID: 80051658497     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. T. Hirai and S. Tenpaku. Using 5 ms segments in concatenative speech synthesis. In Proc. 5th ISCA Speech Syntheis Workshop, June 2004. http://www.ssw5.org/papers/1032.pdf.
2. Z. Ling and R. Wang. HMM-Based unit selection using frame sized speech segments. In Proc. ICSLP, 2006.
3. T. Hirai. Optimization of target cost weights in concatenative speech synthesis with very short segments of 5-ms duration. In Proc. 4rd Joint Meeting of ASA and ASJ, Nov. 2006. Abstract: JASA, Vol. 120, No. 5, Pt. 2, p.3037, 1pSC7.
4. Z. Ling and R. Wang. HMM-based hierarchical unit selection combining Kullback-Leibler divergence with likelihood criterion. In Proc. ICASSP, 2007.
5. HTS version 2.0, 2006. http://hts.ics.nitech.ac.jp/.
6. Y. Sagisaka, K. Takeda, M. Abe, S. Katagiri, T. Umeda, and H. Kuwabara. A large-scale Japanese speech database. In Proc. ICSLP, pages 1089–1092, 1990.
7. K. Tokuda. Reference manual for Speech Signal Processing Toolkit ver. 3.0, 2002. http://kt-lab.ics.nitech.ac.jp/~tokuda/SPTK/.
8. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura. Speech parameter generation algorithms for HMM-based speech synthesis. In Proc. ICASSP, May 2000.
9. Y. Stylianou and A. K. Syrdal. Perceptual and objective detection of discontinuities in concatenative speech synthesis. In Proc. ICASSP, May 2001.
10. A. V. Aho, J. E. Hopcroft, and J. Ullman. Data Structures and Algorithms. Addison-Wesley Pub. Co., 1982.
11. T. Hirai and S. Tenpaku. Refinement of F0 distance measure in 5 ms segment concatenative speech synthesis. In Rec. Spring Meeting, Acoust. Soc. Jpn., March 2007.