Advertisement

An Application of Recurrent Neural Networks to Discriminative Keyword Spotting

  • Santiago Fernández
  • Alex Graves
  • Jürgen Schmidhuber
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4669)

Abstract

The goal of keyword spotting is to detect the presence of specific spoken words in unconstrained speech. The majority of keyword spotting systems are based on generative hidden Markov models and lack discriminative capabilities. However, discriminative keyword spotting systems are currently based on frame-level posterior probabilities of sub-word units. This paper presents a discriminative keyword spotting system based on recurrent neural networks only, that uses information from long time spans to estimate word-level posterior probabilities. In a keyword spotting task on a large database of unconstrained speech the system achieved a keyword spotting accuracy of 84.5%.

Keywords

Hide Markov Model Speech Signal Recurrent Neural Network Automatic Speech Recognition Automatic Speech Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Wilpon, J.G., Rabiner, L.R., Lee, C., Goldman, E.R.: Automatic recognition of keywords in unconstrained speech using hidden Markov models. IEEE Transactions on Acoustics, Speech and Audio Processing 38(11), 1870–1878 (1990)CrossRefGoogle Scholar
  2. 2.
    Benítez, M.C., Rubio, A., García, P., de la Torre, A.: Different confidence measures for word verification in speech recognition. Speech Communication 32, 79–94 (2000)CrossRefGoogle Scholar
  3. 3.
    Silaghi, M.C., Bourlard, H.: Iterative posterior-based keyword spotting without filler models. In: Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop, Keystone - Colorado (U.S.A.) (1999)Google Scholar
  4. 4.
    Silaghi, M.: Spotting subsequences matching an HMM using the average observation probability criteria with application to keyword spotting. In: Proceedings of the 20th National Conference on Artificial Intelligence and the 17th Conference on Innovative Applications of Artificial Intelligence, pp. 1118–1123. Pittsburgh - Pennsylvania (U.S.A.) (2005)Google Scholar
  5. 5.
    Ketabdar, H., Vepa, J., Bengio, S., Bourlard, H.: Posterior based keyword spotting with a priori thresholds. In: Proceedings of the 9th International Conference on Spoken Language Processing, Pittsburgh - Pennsylvania (U.S.A.) (2006)Google Scholar
  6. 6.
    Robinson, A.J.: An application of recurrent nets to phone probability estimation. IEEE Transactions on Neural Networks 5(2), 298–305 (1994)CrossRefGoogle Scholar
  7. 7.
    Bourlard, H.A., Morgan, N.: Connectionist speech recognition: a hybrid approach. Kluwer Academic Publishers, Dordrecht (1994)Google Scholar
  8. 8.
    Keshet, J., Grangier, D., Bengio, S.: Discriminative keyword spotting. In: Workshop on Non-Linear Speech Processing NOLISP, Paris (France) (2007)Google Scholar
  9. 9.
    Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural nets. In: Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh - Pennsylvania (U.S.A.) (2006)Google Scholar
  10. 10.
    Fernández, S., Graves, A., Schmidhuber, J.: Sequence labelling in structured domains with hierarchical recurrent neural networks. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad (India) (2007)Google Scholar
  11. 11.
    Silaghi, M.C., Vargiya, R.: A new evaluation criteria for keyword spotting techniques and a new algorithm. In: Proceedings of InterSpeech (2005)Google Scholar
  12. 12.
    Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18(5–6), 602–610 (2005)CrossRefGoogle Scholar
  13. 13.
    Graves, A., Fernández, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799–804. Springer, Heidelberg (2005)Google Scholar
  14. 14.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  15. 15.
    Gers, F., Schraudolph, N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research 3, 115–143 (2002)CrossRefGoogle Scholar
  16. 16.
    Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 45, 2673–2681 (1997)CrossRefGoogle Scholar
  17. 17.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Santiago Fernández
    • 1
  • Alex Graves
    • 1
  • Jürgen Schmidhuber
    • 1
    • 2
  1. 1.IDSIA, Galleria 2, 6928 Manno-LuganoSwitzerland
  2. 2.TU Munich, Boltzmannstr. 3, 85748 Garching, MunichGermany

Personalised recommendations