Abstract
Hidden Markov Models based text-to-speech (HMM-TTS) synthesis is a technique for generating speech from trained statistical models where spectrum, pitch and durations of basic speech units are modelled altogether. The aim of this work is to describe a Spanish HMM-TTS system using an external machine learning technique to help improving the expressiveness. System performance is analysed objectively and subjectively. The experiments were conducted on a reliably labelled speech corpus, whose units were clustered using contextual factors based on the Spanish language. The results show that the CBR-based F0 estimation is capable of improving the HMM-based baseline performance when synthesizing non-declarative short sentences while the durations accuracy is similar with the CBR or the HMM system.
Thanks to Prof. Dr. Eric Keller, University of Lausanne, for kindly spending a time on verifying this paper. This work has been partially supported by the European Commission, project SALERO FP6 IST-4-027122-IP.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alías, F., Iriondo, I.: Formiga, Ll., Gonzalvo, X., Monzo, C., Sevillano, X.: High quality Spanish restricted-domain TTS oriented to a weather forecast application. In: INTERSPEECH (2005)
Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Simultaneous modeling of spectrum, pitch and duration in hmm-based speech synthesis. In: Eurospeech (1999)
Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Speaker interpolation in HMM-based speech synthesis. In: EUROSPEECH (1997)
Shichiri, K., Sawabe, A., Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Eigenvoices for HMM-based speech synthesis. In: ICSLP (2002)
Latorre, J., Iwano, K., Furui, S.: Cross-language synthesis with a polyglot synthesizer. In: INTERSPEECH, pp. 1477–1480 (2005)
Tokuda, K., Zen, H., Black, A.W.: An HMM-based speech synthesis system applied to English, IEEE SSW (2002)
Maia, R., Zen, H., Tokuda, K., Kitamura, T., Resende, J.F.G.: Towards the development of a Brazilian Portuguese text-to-speech system based on HMM. In: Eurospeech (2003)
Toda, T., Tokuda, K.: A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis. IEICE Transactions E90-D(5), 816–824 (2007)
Donovan, R.E., Woodland, P.C.: A hidden Markov-model-based trainable speech synthesizer. Computer Speech and Language 13, 223–241 (1999)
Iriondo, I., Socoró, J.C., Formiga, L., Gonzalvo, X., Alías, F., Miralles, P.: Modeling and estimating of prosody through CBR. In: JTH 2006 (in Spanish)
Fukada, T., Tokuda, K., Kobayashi, T., Imai, S.: An adaptive algorithm for mel-cepstral analysis of speech. In: ICASSP 1992 (1992)
Alías, F., Monzo, C., Socoró, J.C.: A Pitch Marks Filtering Algorithm based on Restricted Dynamic Programming. In: InterSpeech - ICSLP 2006 (2006)
Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Duration modeling in HMM-based speech synthesis system. In: ICSP 1998 (1998)
Section software in http://www.salle.url.edu/tsenyal
Black, A.W., Taylor, P., Caley, R.: The Festival Speech Synthesis System, http://www.festvox.org/festival
Keller, E., Zellner Keller, B.: How Much Prosody Can You Learn from Twenty Utterances? Linguistik online 17(5/03), 57–78 (2003), http://www.linguistik-online.de/
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gonzalvo, X., Iriondo, I., Socoró, J.C., Alías, F., Monzo, C. (2007). Mixing HMM-Based Spanish Speech Synthesis with a CBR for Prosody Estimation. In: Chetouani, M., Hussain, A., Gas, B., Milgram, M., Zarader, JL. (eds) Advances in Nonlinear Speech Processing. NOLISP 2007. Lecture Notes in Computer Science(), vol 4885. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77347-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-77347-4_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77346-7
Online ISBN: 978-3-540-77347-4
eBook Packages: Computer ScienceComputer Science (R0)