Advertisement

Statistical Text-to-Speech Synthesis of Spanish Subtitles

  • S. Piqueras
  • M. A. del-Agua
  • A. Giménez
  • J. Civera
  • A. Juan
Conference paper
  • 701 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8854)

Abstract

Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish system and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately.

Keywords

video lectures text-to-speech synthesis accessibility 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
  3. 3.
    HMM-Based Speech Synthesis System (HTS), http://hts.sp.nitech.ac.jp
  4. 4.
  5. 5.
    Axelrod, A., He, X., Gao, J.: Domain adaptation via pseudo in-domain data selection. In: Proc. of EMNLP, pp. 355–362 (2011)Google Scholar
  6. 6.
    Bottou, L.: Stochastic gradient learning in neural networks. In: Proceedings of Neuro-Nîmes 1991. EC2, Nimes, France (1991)Google Scholar
  7. 7.
    Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing 20(1), 30–42 (2012)CrossRefGoogle Scholar
  8. 8.
    Erro, D., Sainz, I., Navas, E., Hernaez, I.: Harmonics plus noise model based vocoder for statistical parametric speech synthesis. IEEE Journal of Selected Topics in Signal Processing 8(2), 184–194 (2014)CrossRefGoogle Scholar
  9. 9.
    Fan, Y., Qian, Y., Xie, F., Soong, F.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Proc. of Interspeech (submitted 2014)Google Scholar
  10. 10.
    Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., et al.: Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29(6), 82–97 (2012)CrossRefGoogle Scholar
  11. 11.
    Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proc. of ICASSP, vol. 1, pp. 373–376 (1996)Google Scholar
  12. 12.
    King, S.: Measuring a decade of progress in text-to-speech. Loquens 1(1), e006 (2014)Google Scholar
  13. 13.
    Koehn, P.: Statistical Machine Translation. Cambridge University Press (2010)Google Scholar
  14. 14.
    Kominek, J., Schultz, T., Black, A.W.: Synthesizer voice quality of new languages calibrated with mean mel cepstral distortion. In: Proc. of SLTU, pp. 63–68 (2008)Google Scholar
  15. 15.
    Lopez, A.: Statistical machine translation. ACM Computing Surveys 40(3), 8:1–8:49 (2008)Google Scholar
  16. 16.
    poliMedia: The polimedia video-lecture repository (2007), http://media.upv.es
  17. 17.
    Sainz, I., Erro, D., Navas, E., Hernáez, I., Sánchez, J., Saratxaga, I.: Aholab speech synthesizer for albayzin 2012 speech synthesis evaluation. In: Proc. of IberSPEECH, pp. 645–652 (2012)Google Scholar
  18. 18.
    Seide, F., Li, G., Chen, X., Yu, D.: Feature engineering in context-dependent dnn for conversational speech transcription. In: Proc. of ASRU, pp. 24–29 (2011)Google Scholar
  19. 19.
    Shinoda, K., Watanabe, T.: MDL-based context-dependent subword modeling for speech recognition. Journal of the Acoustical Society of Japan 21(2), 79–86 (2000)CrossRefGoogle Scholar
  20. 20.
    Silvestre-Cerdà, J.A., et al.: Translectures. In: Proc. of IberSPEECH, pp. 345–351 (2012)Google Scholar
  21. 21.
    TED Ideas worth spreading, http://www.ted.com
  22. 22.
    The transLectures-UPV Team.: The transLectures-UPV toolkit (TLK), http://translectures.eu/tlk
  23. 23.
    Toda, T., Black, A.W., Tokuda, K.: Mapping from articulatory movements to vocal tract spectrum with Gaussian mixture model for articulatory speech synthesis. In: Proc. of ISCA Speech Synthesis Workshop (2004)Google Scholar
  24. 24.
    Tokuda, K., Kobayashi, T., Imai, S.: Speech parameter generation from hmm using dynamic features. In: Proc. of ICASSP, vol. 1, pp. 660–663 (1995)Google Scholar
  25. 25.
    Tokuda, K., Masuko, T., Miyazaki, N., Kobayashi, T.: Multi-space probability distribution HMM. IEICE Transactions on Information and Systems 85(3), 455–464 (2002)Google Scholar
  26. 26.
    transLectures: D3.1.2: Second report on massive adaptation, http://www.translectures.eu/wp-content/uploads/2014/01/transLectures-D3.1.2-15Nov2013.pdf
  27. 27.
    Turró, C., Ferrando, M., Busquets, J., Cañero, A.: Polimedia: a system for successful video e-learning. In: Proc. of EUNIS (2009)Google Scholar
  28. 28.
    Videolectures.NET: Exchange ideas and share knowledge, http://www.videolectures.net
  29. 29.
    Wu, Y.J., King, S., Tokuda, K.: Cross-lingual speaker adaptation for HMM-based speech synthesis. In: Proc. of ISCSLP, pp. 1–4 (2008)Google Scholar
  30. 30.
    Yamagishi, J.: An introduction to HMM-based speech synthesis. Tech. rep. Centre for Speech Technology Research (2006), https://wiki.inf.ed.ac.uk/twiki/pub/CSTR/TrajectoryModelling/HTS-Introduction.pdf
  31. 31.
    Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. In: Proc. of Eurospeech, pp. 2347–2350 (1999)Google Scholar
  32. 32.
    Zen, H., Senior, A.: Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis. In: Proc. of ICASSP, pp. 3872–3876 (2014)Google Scholar
  33. 33.
    Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: Proc. of ICASSP, pp. 7962–7966 (2013)Google Scholar
  34. 34.
    Zen, H., Tokuda, K., Black, A.W.: Statistical parametric speech synthesis. Speech Communication 51(11), 1039–1064 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • S. Piqueras
    • 1
  • M. A. del-Agua
    • 1
  • A. Giménez
    • 1
  • J. Civera
    • 1
  • A. Juan
    • 1
  1. 1.MLLP, DSICUniversitat Politècnica de ValènciaValènciaSpain

Personalised recommendations