Minimum generation error training by using original spectrum as reference for log spectral distortion measure

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2009, Pages 4013-4016

  Wu, Yi Jian ^a   Tokuda, Keiichi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

HMM; Log spectral distortion; Minimum generation error; Speech synthesis

Indexed keywords

FFT SPECTRUM; HARMONIC FREQUENCY; HMM; HMM TRAINING; HMM-BASED SPEECH SYNTHESIS; LINE SPECTRAL PAIRS; LOG SPECTRAL DISTORTION; LOG SPECTRAL DISTORTIONS; MINIMUM GENERATION ERROR; REFERENCE SPECTRUM; SAMPLING STRATEGIES; SPECTRAL ENVELOPES; SPEECH WAVEFORMS; WEIGHTING FUNCTIONS;

ACOUSTICS; HIDDEN MARKOV MODELS; SIGNAL PROCESSING; SPEECH SYNTHESIS; VECTOR QUANTIZATION;

FAST FOURIER TRANSFORMS;

EID: 67650797362     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4960508     Document Type: Conference Paper

References (12)

1. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Speech synthesis from HMMs using dynamic features," in Proc. of ICASSP, pp. 389-392, 1996.
2. J. Yamagishi, H. Zen, T. Toda, and K. Tokuda, "Speaker-independent HMM-based speech synthesis system - HTS-2007 system for the Blizzard Challenge 2007", in Blizzard Challenge 2007.
3. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMMbased speech synthesis," in Proc. of ICASSP, vol. 5, pp. 2347-2350, 1999.
4. K. Tokuda, T. Kobayashi, and S. Imai, "Speech parameter generation fromHMMusing dynamic features," in Proc. of ICASSP, pp. 660-663, 1995.
5. Y.-J. Wu and R.H. Wang, "Minimum generation error training for HMM-based speech synthesis," in Proc. of ICASSP, vol. 1, pp. 889-892, 2006.
6. F. Itakura, "Line spectrum representation of linear predictive coeffi-cients of speech signals," in J. Acoust. Soc. Amer., vol. 57, p. 535(a), p. s35(A), 1975.
7. Y.-J. Wu and K. Tokuda, "Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis," in Proc. of Interspeech, pp. 577-580, 2008.
8. H. Kawahara, I. Masuda-Katsuse and A. deCheveigne, "Restructuring speech representations using pitch-adaptive time-frequency smoothing and an instanta-neous-frequency-based F0 extraction: possible role of a repetitive structure in sounds," in Speech Communication, vol. 27, pp. 187-207, 1999.
9. M. Akamine and T. Kagoshima, "Analytic generation of synthesis units by closed loop training for totally speaker driven text to speech system (TOS drive TTS)," in Proc. of ICSLP, 1998.
10. T. Toda and K. Tokuda, "Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM," in Proc of ICASSP, pp. 3925-3928, 2008.
11. S. Amari, "A theory of adaptive pattern classifiers," IEEE Trans. Electron. Comput., vol. EC-16, no. 3, pp. 299-307, 1967.
12. K. Tokuda, T. Masuko, N. Miyazaki, and T. Kobayashi, "Hidden markov models based on multi-space probability distribution for pitch pattern modeling," in Proc. of ICASSP, pp. 229-232, 1999.