Czech HMM-Based Speech Synthesis
In this paper, first experiments on statistical parametric HMM-based speech synthesis for the Czech language are described. In this synthesis method, trajectories of speech parameters are generated from the trained hidden Markov models. A final speech waveform is synthesized from those speech parameters. In our experiments, spectral properties were represented by mel cepstrum coefficients. For the waveform synthesis, the corresponding MLSA filter excited by pulses or noise was utilized. Beside that basic setup, a high-quality analysis/synthesis system STRAIGHT was employed for more sophisticated speech representation. For a more robust model parameter estimation, HMMs are clustered by using decision tree-based context clustering algorithm. For this purpose, phonetic and prosodic contextual factors proposed for the Czech language are taken into account. The created clustering trees are also employed for synthesis of speech units unseen within the training stage. The evaluation by subjective listening tests showed that speech produced by the combination of HMM-based TTS system and STRAIGHT is of comparable quality as speech synthesised by the unit selection TTS system trained from the same speech data.
KeywordsHMM-based speech synthesis TTS Czech language
Unable to display preview. Download preview PDF.
- 2.Kawahara, H., Masuda-Katsuse, I., de Cheveigne, A.: Restructuring Speech Representations using a Pitch-Adaptive Time-Frequency Smoothing and an Instantaneous-Frequency-based F0 Extraction: Possible Role of a Repetitive Structure in Sounds. Speech Communication 27, 187–207 (1999)CrossRefGoogle Scholar
- 3.Tokuda, K., Zen, H., Black, A.W.: An HMM-based Speech Synthesis System Applied to English. In: Proc. of IEEE Workshop on Speech Synthesis, pp. 227–230 (2002)Google Scholar
- 4.HMM-based Speech Synthesis System (HTS), http://hts.sp.nitech.ac.jp
- 5.Speech Signal Processing Toolkit (SPTK), http://sp-tk.sourceforge.net
- 7.Czech SAMPA, http://www.phon.ucl.ac.uk/home/sampa/czech-uni.htm
- 8.Matoušek, J., Hanzlíček, Z., Tihelka, D.: Hybrid Syllable/Triphone Speech Synthesis. In: Proc. of Interspeech 2005, Lisbon, Portugal, pp. 2529–2532 (2005)Google Scholar
- 9.Romportl, J., Matoušek, J., Tihelka, D.: Advanced Prosody Modelling. In: Sojka, P., Kopeček, I., Pala, K. (eds.) TSD 2004. LNCS (LNAI), vol. 3206, pp. 441–447. Springer, Heidelberg (2004)Google Scholar
- 10.Tihelka, D., Matoušek, J.: Unit Selection and its Relation to Symbolic Prosody: A New Approach. In: Proc. of Interspeech 2006 – ICSLP, Pittsburgh, Pennsylvania, vol. 1, pp. 2042–2045 (2006)Google Scholar
- 12.STRAIGHT, a speech analysis, modification and synthesis system, http://www.wakayama-u.ac.jp/~kawahara/STRAIGHTadv/index_e.html
- 14.Maia, R., Toda, T., Zen, H., Nankaku, Y., Tokuda, K.: An Excitation Model for HMM-Based Speech Synthesis Based on Residual Modelling. In: Proc. of 6th ISCA Workshop on Speech Synthesis, pp. 131–136 (2007)Google Scholar