Abstract
The absence of alternatives/variants is a dramatical limitation of text-to-speech (TTS) synthesis compared to the variety of human speech. This chapter introduces the use of speech alternatives/variants in order to improve TTS synthesis systems. Speech alternatives denote the variety of possibilities that a speaker has to pronounce a sentence—depending on linguistic constraints, specific strategies of the speaker, speaking style, and pragmatic constraints. During the training, symbolic and acoustic characteristics of a unit-selection speech synthesis system are statistically modelled with context-dependent parametric models (Gaussian mixture models (GMMs)/hidden Markov models (HMMs)). During the synthesis, symbolic and acoustic alternatives are exploited using a Generalized Viterbi Algorithm (GVA) to determine the sequence of speech units used for the synthesis. Objective and subjective evaluations support evidence that the use of speech alternatives significantly improves speech synthesis over conventional speech synthesis systems. Moreover, speech alternatives can also be used to vary the speech synthesis for a given text. The proposed method can easily be extended to HMM-based speech synthesis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Atterer, M., and E. Klein. 2002. Integrating linguistic and performance-based constraints for assigning phrase breaks. In International Conference on Computational Linguistics, Taipei, Taiwan, 995–998.
Bell, P., T. Burrows, and P. Taylor. 2006. Adaptation of prosodic phrasing models. In Speech Prosody, Dresden, Germany.
Black, A., and P. Taylor. 1994. Assigning intonation elements and prosodic phrasing for English speech synthesis from high level linguistic input. In International Conference on Spoken Language Processing, Yokohama, Japan, 715–718.
Bulyko, I., and M. Ostendorf. 2001. Joint prosody prediction and unit selection for concatenative speech synthesis. In International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, USA, 781–784.
Gao, B., Y. Qian, Z. Wu, and F. Soong. 2008. Duration refinement by jointly optimizing state and longer unit likelihood. In Interspeech, Brisbane, Australia, 2266–2269.
Hashimoto, T. 1987. A list-type reduced-constraint generalization of the Viterbi algorithm. IEEE Transactions on Information Theory 33 (6): 866–876.
Hunt, A., and A. Black. 1996. Unit selection in a concatenative speech synthesis system using a large speech database. In International Conference on Audio, Speech, and Signal Processing, 373–376.
Ingulfen, T., T. Burrows, and S. Buchholz. 2005. Influence of syntax on prosodic boundary prediction. In Interspeech, Lisboa, Portugal, 1817–1820.
Latorre, J., and M. Akamine. 2008. Multilevel parametric-base F0 model for speech synthesis. In Interspeech, Brisbane, Australia, 2274–2277.
Obin, N. 2011. MeLos: Analysis and modelling of speech prosody and speaking style. PhD Thesis, Ircam - UPMC.
Obin, N., P. Lanchantin, A. Lacheret, and X. Rodet. 2010a. Towards improved HMM-based speech synthesis using high-level syntactical features. In Speech Prosody, Chicago, USA
Obin, N., A. Lacheret, and X. Rodet. 2010b. HMM-based prosodic structure model using rich linguistic context. In Interspeech, Makuhari, Japan, 1133–1136.
Obin, N., P. Lanchantin, A. Lacheret, and X. Rodet. 2011a. Discrete/continuous modelling of speaking style in HMM-based speech synthesis: Design and evaluation. In Interspeech, Florence, Italy, 2785–2788.
Obin, N., A. Lacheret, and X. Rodet. 2011b. Stylization and trajectory modelling of short and long term speech prosody variations. In Interspeech, Florence, Italy, 2029–2032.
Obin, N., P. Lanchantin, A. Lacheret, and X. Rodet. 2011c. Reformulating prosodic break model into segmental HMMs and information fusion. In Interspeech, Florence, Italy, 1829–1832.
Ostendorf, M., and N. Veilleux. 1994. A hierarchical stochastic model for automatic prediction of prosodic boundary location. Journal of Computational Linguistics 20 (1): 27–54.
Parlikar, A., and A. W. Black. 2012. Modeling pause-duration for style-specific speech synthesis. In Interspeech, Portland, Oregon, USA, 446–449.
Parlikar, A., and A. W. Black. 2013. Minimum error rate training for phrasing in speech synthesis. In Speech Synthesis Workshop (SSW), Barcelona, Spain, 13–17.
Qian, Y., Z. Wu, and F. K. Soong. 2009. Improved prosody generation by maximizing joint likelihood of state and longer units. In International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan, 3781–3784.
Schmid, H., and M. Atterer. 2004. New statistical methods for phrase break prediction. In International Conference on Computational Linguistics, Geneva, Switzerland, 659–665.
Toda, T., and K. Tokuda. 2007. A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Transactions on Information and Systems 90 (5): 816–824.
Tokuda, K., H. Zen, and T. Kitamura. 2003. Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features. In European Conference on Speech Communication and Technology, Geneva, Switzerland, 865–868.
Veaux, C., and X. Rodet. 2011. Prosodic control of unit-selection speech synthesis: A probabilistic approach. In International Conference on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, 5360–5363.
Veaux, C., P. Lanchantin, and X. Rodet. 2010. Joint prosodic and segmental unit selection for expressive speech synthesis. In Speech Synthesis Workshop (SSW7), Kyoto, Japan, 323–327.
Yan, Z.-J., Y. Qian, and F. K. Soong. 2009. Rich context modeling for high quality HMM-based TTS. In Interspeech, Brighton, UK, 4025–4028.
Yoshimura, T., K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura. 1999. Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In European Conference on Speech Communication and Technology, Budapest, Hungary, 2347–2350.
Zen, H., K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura. 2004. Hidden semi-Markov model based speech synthesis. In International Conference on Spoken Language Processing, Jeju Island, Korea, 1397–1400.
Zen, H., K. Tokuda, and A. Black. 2009. Statistical parametric speech synthesis. Speech Communication 51 (11): 1039–1064.
Zen, A., A. Senior, and M. Schuster. 2013. Statistical parametric speech synthesis using deep neural networks. In International Conference on Acoustics, Speech, and Signal Processing, Vancouver, Canada, 7962–7966.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Obin, N., Veaux, C., Lanchantin, P. (2015). Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human. In: Hirose, K., Tao, J. (eds) Speech Prosody in Speech Synthesis: Modeling and generation of prosody for high quality and flexible speech synthesis. Prosody, Phonology and Phonetics. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45258-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-662-45258-5_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45257-8
Online ISBN: 978-3-662-45258-5
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)