Abstract
Our research team set the goal of creating a modern speech synthesis system for the Kazakh language. One of the most important components of such system is the phoneme duration prediction. In this article, we present our work on the creation of such a classifier. We managed to develop a detector based on deep neural network, using for this purpose a minimum number of input linguistic and phonetic parameters. Based on the learning results, the proposed detector predicts the duration of phonemes on test data with a deviation of 20–25 ms on average.
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
Similar content being viewed by others
References
Arman K., Rybin, S.V., Matveev, Y.N., Kaziyeva, N., Burambayeva, N.,: Modeling pause for the synthesis of Kazakh speech. In: Proceedings of the Fourth International Conference on Engineering & MIS 2018 (ICEMIS 2018), Article 1, 4 p. ACM, New York, NY, USA, (2018). https://doi.org/10.1145/3234698.3234699
Chen, B., Bian, T., Yu, K.: Discrete duration model for speech synthesis. In: 18th Annual Conference of the International Speech Communication Association, Interspeech 2017, Stockholm, Sweden, 20–24 August 2017, pp. 789–793 (2017)
Fernandez, R., Rendel, A., Ramabhadran, B., Hoory, R.: Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks. In: 15th Annual Conference of the International Speech Communication Association, INTERSPEECH 2014, Singapore, 14–18 September 2014, pp. 2268–2272 (2014)
Foltz, P.W.: Latent semantic analysis for text-based research. Behav. Res. Methods Instrum. Comput. 28(2), 197–202 (1996). https://doi.org/10.3758/BF03204765
Henter, G.E., Ronanki, S., Watts, O., Wester, M., Wu, Z., King, S.: Robust TTS duration modelling using DNNs. In: Proceedings of the ICASSP, vol. 41. IEEE, Shanghai, March 2016. http://homepages.inf.ed.ac.uk/ghenter/pubs/henter2016robust.pdf
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Kaliyev, A., Rybin, S.V., Matveev, Y.: The pausing method based on brown clustering and word embedding. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 741–747. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66429-3_74
Karpov, A., Verkhodanova, V.: Speech technologies for under-resourced languages of the world 2015, pp. 117–135 (2015)
Khomitsevich, O., Mendelev, V., Tomashenko, N., Rybin, S., Medennikov, I., Kudubayeva, S.: A bilingual Kazakh-Russian system for automatic speech recognition and synthesis. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS (LNAI), vol. 9319, pp. 25–33. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23132-7_3
Koo, T., Carreras, X., Collins, M.: Simple semi-supervised dependency parsing. In: Proceedings of ACL 2008: HLT, pp. 595–603. Association for Computational Linguistics, Columbus, June 2008. http://www.aclweb.org/anthology/P/P08/P08-1068
Miller, S., Guinness, J., Zamanian, A.: Name tagging with word clusters and discriminative training. In: Susan Dumais, D.M., Roukos, S. (eds.) HLT-NAACL 2004: Main Proceedings, pp. 337–342. Association for Computational Linguistics, Boston, 2–7 May 2004. http://www.aclweb.org/anthology/N04-1043
Ronanki, S., Watts, O., King, S., Henter, G.E.: Median-based generation of synthetic speech durations using a non-parametric approach. CoRR abs/1608.06134 (2016). http://arxiv.org/abs/1608.06134
Zen, H., Sak, H.: Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4470–4474 (2015)
Zen, H., Senior, A.W.: Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, 4–9 May 2014, pp. 3844–3848 (2014). https://doi.org/10.1109/ICASSP.2014.6854321
Acknowledgments
This work was partially financially supported by the Government of the Russian Federation (Grant 08-08) and by the initial funding from the ITMO University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Kaliyev, A., Rybin, S.V., Matveev, Y.N. (2018). Phoneme Duration Prediction for Kazakh Language. In: Karpov, A., Jokisch, O., Potapova, R. (eds) Speech and Computer. SPECOM 2018. Lecture Notes in Computer Science(), vol 11096. Springer, Cham. https://doi.org/10.1007/978-3-319-99579-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-99579-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99578-6
Online ISBN: 978-3-319-99579-3
eBook Packages: Computer ScienceComputer Science (R0)