Quantized HMMs for low footprint text-to-speech synthesis

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 837-840

  Gutkin, Alexander ^a   Gonzalvo, Xavi ^a   Breuer, Stefan ^a   Taylor, Paul ^a  

^a Phonetic Arts Ltd   (United Kingdom)

Author keywords

HMM based speech synthesis; Low footprint; Quantized HMM

Indexed keywords

ECONOMIC AND SOCIAL EFFECTS; HIDDEN MARKOV MODELS; SPEECH COMMUNICATION; SPEECH SYNTHESIS; SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; EMBEDDED DEVICE; GENERATION ALGORITHM; HMM-BASED SPEECH SYNTHESIS; LOW-FOOTPRINT; MEMORY REQUIREMENTS; QUANTIZED HMM; SPECTRAL DISTORTIONS; HIDDEN-MARKOV MODELS; HMM-BASED; PERFORMANCE; STANDARD ML; TTS SYSTEMS;

SPEECH RECOGNITION; SPEECH SYNTHESIS;

EID: 79959839868     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. A. Hunt and A. W. Black, "Unit selection in a concatenative speech synthesis system using a large speech database," in Proc. ICASSP, vol. 1, Atlanta, Georgia, Jun. 1996, pp. 373-376.
2. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," in Proc. Eurospeech, vol. 5, Budapest, Hungary, Sep. 1999, pp. 2347-2350.
3. Z. H. Ling and R. H. Wang, "HMM-based hierarchical unit selection combining Kullback-Leibler divergence with likelihood criterion," in Proc. ICASSP, Honolulu, USA, 2007, pp. 1245-1248.
4. X. Gonzalvo, A. Gutkin, J. C. Socoro, I. Iriondo, and P. Taylor, "Local minimum generation error criterion for hybrid HMM speech synthesis," in Proc. ICSLP, Brighton, UK, 2009, pp. 416-419.
5. H. Zen, K. Tokuda, and A. W. Black, "Statistical parametric speech synthesis," Speech Communication, vol. 51, no. 11, pp. 1039-1064, Nov. 2009.
6. A. W. Black and P. Taylor, "Automatically clustering similar units for unit selection in speech synthesis," in Proc. Eurospeech'97, Rhodes, Greece, Sep. 1997, pp. 601-604.
7. D. Chazan, R. Hoory, Z. Kons, D. Silberstein, and A. Sorin, "Reducing the footprint of the IBM trainable speech synthesis system," in Proc. ICSLP, Denver, USA, Sep. 2002, pp. 2381-2384.
8. M. Vasilache, "Speech recognition using HMMs with quantized parameters," in Proc. ICSLP, vol. 1, Beijing, China, Oct. 2000, pp. 441-443.
9. J. H. Kim, R. Haimi-Cohen, and F. K. Soong, "Hidden Markov models with divergence based vector quantized variances," in Proc. ICASSP, vol. 1, Phoenix, USA, Mar. 1999, pp. 125-128.
10. K. Filali, X. Li, and J. Bilmes, "Algorithms for data-driven ASR parameter quantization," Computer Speech and Language, vol. 20, no. 4, pp. 625-643, Oct. 2006. (Pubitemid 44142008)
11. E. Bocchieri and B. Mak, "Subspace Distribution Clustering for Continuous Observation Density Hidden Markov Models," in Proc. Eurospeech, vol. 1, Rhodes, Greece, 1997, pp. 107-110.
12. I. Kiss, J. Leppänen, and S. Sivadas, "Nokia's system for TC-STAR EPPS English ASR evaluation task," in Proc. TC-STAR Workshop on Speech-to-Speech Translation, Barcelona, Spain, Jun. 2006, pp. 129-132.
13. K. Oura, H. Zen, Y. Nankaku, A. Lee, and K. Tokuda, "Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems," in Proc. ICSLP, Brighton, UK, 2009, pp. 1759-1762.
14. M. Vasilache and O. Viikki, "Speaker adaptation of quantized parameter HMMs," in Proc. Eurospeech, Aalborg, Denmark, Sep. 2001, pp. 1265-1268.
15. J. Leppänen and I. Kiss, "Comparison of low footprint acoustic modeling techniques for embedded ASR systems," in Proc. IC-SLP, Lisbon, Portugal, Sep. 2005, pp. 2965-2968.
16. Y. Linde, A. Buzo, and R. M. Gray, "An algorithm for vector quantizer design," IEEE Transactions on Communications, vol. 28, no. 1, pp. 84-95, Jan. 1980.
17. 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 Proc. of BLZ3, Bonn, Germany, Sep. 2009, p. 8.
18. L. Zouari and G. Choletta, "Effcient codebooks for fast and accurate low resource ASR systems," Speech Communication, vol. 51, no. 9, pp. 732-743, Sep. 2009.
19. J. V. Davis and I. S. Dhillon, "Differential Entropic Clustering of Multivariate Gaussians," in Neural Information Processing Systems (NIPS), B. Scholkopf, J. Platt, and T. Hoffman, Eds. MIT Press, 2006, pp. 337-344.