Language Identification Using Time Delay Neural Network D-Vector on Short Utterances

  • Maxim Tkachenko
  • Alexander Yamshinin
  • Nikolay Lyubimov
  • Mikhail Kotov
  • Marina Nastasenko
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9811)

Abstract

This paper describes d-vector language identification (LID) system on short utterances using time delay neural network (TDNN) acoustic model for the speech recognition task. The acoustic TDNN model is chosen for ASR system of ICQ messenger and it’s applied for the LID task. We compared LID TDNN d-vector results to i-vector baseline. It was found that the TDNN system performance is close at any durations while i-vector shows good results only at long time. Open-set test is conducted. Relative improvement of 5.5 % over the i-vector system is shown.

Keywords

Language identification I-vector D-vector Speech recognition acoustic model Neural networks 

References

  1. 1.
    Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19, 788–798 (2011). IEEE PressCrossRefGoogle Scholar
  2. 2.
    Martinez, D., Plchot, O., Burget, L., Glembek, O., Matejka, P.: Language recognition in ivectors space. In: 12th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 861–864. ISCA, Florence (2011)Google Scholar
  3. 3.
    Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645-6649. IEEE Press, Vancouver (2013)Google Scholar
  4. 4.
    Gonzalez-Dominguez, J., Lopez-Moreno, I., Sak, H., Gonzalez-Rodriguez, J., Moreno, P.: Automatic language identification using long short-term memory recurrent neural networks. In: 16th Annual Conference of the International Speech Communication Association (INTERSPEECH). ISCA, Dresden (2015)Google Scholar
  5. 5.
    Zazo, R., Lozano-Diez, A., Gonzalez-Dominguez, J., Toledano, D., Gonzalez-Rodriguez, J.: Language identification in short utterances using long short-term memory (LSTM) recurrent neural networks. PLoS ONE 11(1), e0146917 (2016)CrossRefGoogle Scholar
  6. 6.
    Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: 16th Annual Conference of the International Speech Communication Association (INTERSPEECH). ISCA, Dresden (2015)Google Scholar
  7. 7.
    Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Press, Singapore (2014)Google Scholar
  8. 8.
    Kenny, P., Oullet, P., Dehak, N., Gupta, V., Dumouchel, P.: A study of interspeaker variability in speaker verification. IEEE Trans. Audio Speech Lang. Process. 16, 980–988 (2008). IEEE PressCrossRefGoogle Scholar
  9. 9.
    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, Hawaii (2011)Google Scholar
  10. 10.
    Testarium. Research tool and experiment repository. http://testarium.makseq.com

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Maxim Tkachenko
    • 1
  • Alexander Yamshinin
    • 1
  • Nikolay Lyubimov
    • 3
  • Mikhail Kotov
    • 2
  • Marina Nastasenko
    • 1
  1. 1.Vector I LLCMoscowRussia
  2. 2.ASM Solutions LLCMoscowRussia
  3. 3.Lomonosov Moscow State UniversityMoscowRussia

Personalised recommendations