Advertisement

Measuring the Effect of Reverberation on Statistical Parametric Speech Synthesis

  • Marvin Coto-JiménezEmail author
Conference paper
  • 18 Downloads
Part of the Communications in Computer and Information Science book series (CCIS, volume 1087)

Abstract

Text-to-speech (TTS) synthesis is the technique of generating intelligible speech from a given text. The most recent techniques for TTS are based on machine learning, implementing systems which learn linguistic specifications and their corresponding parameters of the speech signal. Given the growing interest in implementing verbal communication systems in different devices, such as cell phones, car navigation system and personal assistants, it is important to use speech data from many sources. The speech recordings available for this purpose are not always generated with the best quality. For example, if an artificial voice is created from historical recordings, or a voice created from a person whom only a small set of recordings exists. In these cases, there is an additional challenge due to the adverse conditions in the data. Reverberation is one of the conditions that can be found in these cases, a product of the different trajectories that a speech signal can take in an environment before registering through a microphone. In the present work, we quantitatively explore the effect of different levels of reverberation on the quality of artificial voice generated with those references. The results show that the quality of the generated artificial speech is affected considerably with any level of reverberation. Thus, the application of algorithms for speech enhancement must be taken always into consideration before and after any process of TTS.

Keywords

Hidden Markov Models PESQ Reverberation Speech synthesis 

Notes

Acknowledgements

This work was supported by the University of Costa Rica (UCR), Project No. 322-B9-105.

References

  1. 1.
    Black, A.W.: Unit selection and emotional speech. In: Eighth European Conference on Speech Communication and Technology (2003)Google Scholar
  2. 2.
    Coto-Jiménez, M.: Improving post-filtering of artificial speech using pre-trained LSTM neural networks. Biomimetics 4(2), 39 (2019)CrossRefGoogle Scholar
  3. 3.
    Coto-Jiménez, M., Goddard-Close, J.: LSTM deep neural networks postfiltering for enhancing synthetic voices. Int. J. Pattern Recognit Artif Intell. 32(01), 1860008 (2018)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Holmes, W.: Speech Synthesis and Recognition. CRC Press, Boca Raton (2001)Google Scholar
  5. 5.
    ITU-T, R.P.: 862.1: Mapping function for transforming P. 862 raw result scores to MOS-LQO. International Telecommunication Union, Geneva, Switzerland, November 2003 (2003)Google Scholar
  6. 6.
    Karhila, R., Remes, U., Kurimo, M.: Noise in HMM-based speech synthesis adaptation: analysis, evaluation methods and experiments. IEEE J. Sel. Top. Signal Process. 8(2), 285–295 (2013)CrossRefGoogle Scholar
  7. 7.
    King, S.: Measuring a decade of progress in text-to-speech. Loquens 1(1), e006 (2014)CrossRefGoogle Scholar
  8. 8.
    Kominek, J., Black, A.W.: The CMU arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)Google Scholar
  9. 9.
    Lee, J., Song, K., Noh, K., Park, T.J., Chang, J.H.: DNN based multi-speaker speech synthesis with temporal auxiliary speaker id embedding. In: 2019 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1–4. IEEE (2019)Google Scholar
  10. 10.
    Moreno Pimentel, J., et al.: Effects of noise on a speaker-adaptive statistical speech synthesis system (2014)Google Scholar
  11. 11.
    Öztürk, M.G., Ulusoy, O., Demiroglu, C.: DNN-based speaker-adaptive postfiltering with limited adaptation data for statistical speech synthesis systems. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7030–7034. IEEE (2019)Google Scholar
  12. 12.
    Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3617–3621. IEEE (2019)Google Scholar
  13. 13.
    Rix, A.W., Hollier, M.P., Hekstra, A.P., Beerends, J.G.: Perceptual evaluation of speech quality (PESQ) the new itu standard for end-to-end speech quality assessment Part I-time-delay compensation. J. Audio Eng. Soc. 50(10), 755–764 (2002)Google Scholar
  14. 14.
    Stewart, R., Sandler, M.: Database of omnidirectional and B-format room impulse responses. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 165–168. IEEE (2010)Google Scholar
  15. 15.
    Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., Oura, K.: Speech synthesis based on hidden Markov models. Proc. IEEE 101(5), 1234–1252 (2013)CrossRefGoogle Scholar
  16. 16.
    Tokuda, K., Zen, H., Black, A.W.: An HMM-based speech synthesis system applied to English. In: IEEE Speech Synthesis Workshop, pp. 227–230 (2002)Google Scholar
  17. 17.
    Valentini-Botinhao, C., Wang, X., Takaki, S., Yamagishi, J.: Speech enhancement for a noise-robust text-to-speech synthesis system using deep recurrent neural networks. In: Interspeech, pp. 352–356 (2016)Google Scholar
  18. 18.
    Valentini-Botinhao, C., Yamagishi, J.: Speech enhancement of noisy and reverberant speech for text-to-speech. IEEE/ACM Trans. Audio Speech Lang. Process. 26(8), 1420–1433 (2018)CrossRefGoogle Scholar
  19. 19.
    Valin, J.M., Skoglund, J.: LPCNet: improving neural speech synthesis through linear prediction. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5891–5895. IEEE (2019)Google Scholar
  20. 20.
    Wang, X., Lorenzo-Trueba, J., Takaki, S., Juvela, L., Yamagishi, J.: A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4804–4808. IEEE (2018)Google Scholar
  21. 21.
    Wang, X., Takaki, S., Yamagishi, J.: Investigating very deep highway networks for parametric speech synthesis. Speech Commun. 96, 1–9 (2018)CrossRefGoogle Scholar
  22. 22.
    Wen, J.Y., Gaubitch, N.D., Habets, E.A., Myatt, T., Naylor, P.A.: Evaluation of speech dereverberation algorithms using the MARDY database. In: Proceedings of the International Workshop Acoustic Echo Noise Control (IWAENC). Citeseer (2006)Google Scholar
  23. 23.
    Zen, H., et al.: The HMM-based speech synthesis system (HTS) version 2.0. In: SSW, pp. 294–299. Citeseer (2007)Google Scholar
  24. 24.
    Zen, H., et al.: Recent development of the HMM-based speech synthesis system (HTS) (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.PRIS-Lab, Escuela de Ingeniería Eléctrica, Universidad de Costa RicaSan PedroCosta Rica

Personalised recommendations