Exploring the Effect of Tones for Myanmar Language Speech Recognition Using Convolutional Neural Network (CNN)

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 781)

Abstract

Tone information is very helpful to improve automatic speech recognition (ASR) performance in tonal languages such as Mandarin, Thai, Vietnamese, etc. Since Myanmar language is being considered as a tonal language, the effect of tones on both syllable and word-based ASR performance has been explored. In this work, experiments are done based on the modeling of tones by integrating them into the phoneme set and incorporating them into the Convolutional Neural Network (CNN), state-of-the-art acoustic model. Moreover, to be more effective tone modeling, tonal questions are used to build the phonetic decision tree. With tone information, experiments show that compared with Deep Neural Network (DNN) baseline, the performance of CNN model achieves nearly 2% for word-based ASR or more than 2% for syllable-based ASR improvement over DNN model. As a result, the CNN model with tone information gets 2.43% word error rate (WER) or 2.26% syllable error rate (SER) reductions than without using it.

Keywords

Tone information Automatic Speech Recognition (ASR) Tonal language Deep Neural Network (DNN) Convolutional Neural Network (CNN) 

References

  1. 1.
    Sainath, T.N., Mohamed, A., Kingsbury, B., Ramabhadran, B.: Deep convolutional neural networks for LVCSR. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, Vancouver, pp. 8614–8618, 26–31 May 2013Google Scholar
  2. 2.
    Sainath, T.N., Kingsbury, B., Mohamed, A., Dahl, G.E., Saon, G., Soltau, H., Beran, T., Aravkin, A.Y., Ramabhadran, B.: Improvements to deep convolutional neural networks for LVCSR, In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, pp. 315–320, 8–12 December 2013Google Scholar
  3. 3.
    Sainath, T.N., Kingsbury, B., Saon, G., Soltau, H., Mohamed, A., Dahl, G.E., Ramabhadran, B.: Deep convolutional neural networks for large-scale speech tasks. Neural Netw. 64, 39–48 (2015)CrossRefGoogle Scholar
  4. 4.
    Sercu, T., Puhrsch, C., Kingsbury, B., LeCun, Y.: Very deep multilingual convolutional neural networks for LVCSR. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, pp. 4955–4959, 20–25 March 2016Google Scholar
  5. 5.
    Hu, X., Saiko, M., Hori, C.: Incorporating tone features to convolutional neural network to improve Mandarin/Thai speech recognition. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014, Chiang Mai, pp. 1–5, 9–12 December 2014Google Scholar
  6. 6.
    Nguyen, V.H., Luong, C.M., Vu, T.T.: Tonal phoneme based model for Vietnamese LVCSR. In: 2015 International Conference Oriental COCOSDA Held Jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), Shanghai, pp. 118–122, 28–30 October 2015Google Scholar
  7. 7.
    Naing, H.M.S., Hlaing, A.M., Pa, W.P., Hu, X., Thu, Y.K., Hori, C., Kawai, H.: A Myanmar large vocabulary continuous speech recognition system. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, (APSIPA 2015), Hong Kong, pp. 320–327, 16–19 December 2015Google Scholar
  8. 8.
    Htun, U.T.: Acoustic Phonetics and the Phonology of the Myanmar Language. School of Human Communication Sciences, La Trobe University, Melbourne (2007)Google Scholar
  9. 9.
    Luong, H.T., Vu, H.Q.: A non-expert Kaldi recipe for Vietnamese speech recognition system. In: Proceedings of WLSI/OIAF4HLT, Osaka, pp. 51–55, 12 December 2016Google Scholar
  10. 10.
    Mon, A.N., Pa, W.P., Thu, Y.K.: Building HMM-SGMM continuous automatic speech recognition on Myanmar web news. In: Proceedings of 15th International Conference on Computer Applications (ICCA 2017), pp. 446–453 (2017)Google Scholar
  11. 11.
    Soe, W., Thein, Y.: Syllable-based speech recognition system for Myanmar. Int. J. Comput. Sci. Eng. Inf. Technol. (IJCSEIT) 1–13 (2015)Google Scholar
  12. 12.
    Nwe, T.T., Myint, T.: Myanmar language speech recognition with hybrid artificial neural network and Hidden Markov Model. In: Proceedings of 2015 International Conference on Future Computational Technologies (ICFCT 2015), Singapore, pp. 116–122, 29–30 March 2015Google Scholar
  13. 13.
    Khaing, I.: Myanmar continuous speech recognition system based on DTW and HMM. Int. J. Innov. Eng. Technol. (IJIET) 2(1), 78–83 (2013). ISSN 2319-1058Google Scholar
  14. 14.
    Pa, W.P., Thu, Y.K., Finch, A., Sumita, E.: Word boundary identification for Myanmar text using conditional random fields. In: Zin, T.T., Lin, J.C.-W., Pan, J.-S., Tin, P., Yokota, M. (eds.) GEC 2015. AISC, vol. 388, pp. 447–456. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-23207-2_46 CrossRefGoogle Scholar
  15. 15.
    Thu, Y.K., Pa, W.P., Finch, A., Ni, J., Sumita, E., Hori, C.: The application of phrase based statistical machine translation techniques to Myanmar grapheme to phoneme conversion. In: Computational Linguistics - 14th International Conference of the Pacific Association for Computaitonal Linguistics, PACLING 2015, Bali, Revised Selected Papers, pp. 238–250, 19–21 May 2015Google Scholar
  16. 16.
    Myanmar-English Dictionary: Department of the Myanmar Language Commission. Yangon, Ministry of Education, Myanmar (1993)Google Scholar
  17. 17.
    Stolcke, A.: SRILM - An Extensible Language Modeling Toolkit, pp. 901–904 (2002)Google Scholar
  18. 18.
    Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society. IEEE Catalog No.: CFP11SRW-USB, December 2011Google Scholar
  19. 19.
    Ghahremani, P., BabaAli, B., Povey, D., Riedhammer, K., Trmal, J., Khudanpur, S.: A pitch extraction algorithm tuned for automatic speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, pp. 2494–2498, 4–9 May 2014Google Scholar
  20. 20.
    Hirsimäki, T.: A review: decision trees in speech recognition, 27 May 2003Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Natural Language Processing LaboratoryUniversity of Computer StudiesYangonMyanmar
  2. 2.Artificial Intelligence LaboratoryOkayama Prefectural UniversityOkayamaJapan

Personalised recommendations