Speech Keyword Spotting with Rule Based Segmentation

  • Mindaugas Greibus
  • Laimutis Telksnys
Part of the Communications in Computer and Information Science book series (CCIS, volume 403)


Speech keyword spotting is a retrieval of all instances of a given keyword in utterances. This paper presents improved template based keyword spotting algorithm. It solves speaker dependent speech segment detection in continuous speech with small vocabulary. The rules based segmentation algorithm allows to extract quasi-syllables. We evaluated the algorithm by experimental with synthetic signals. The algorithm results outperform classical keyword spotting algorithm with experimental data.


Speech processing Speech segmentation Keyword spotting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Maskeliunas, R., Ratkevicius, K., Rudzionis, V.: Some aspects of voice user interfaces development for internet and computer control applications. Electronics and Electrical Engineering 19(2), 53–56 (2013)CrossRefGoogle Scholar
  2. 2.
    Veveo: Conversational interfaces whitepaper. Technical report, Veveo (2012)Google Scholar
  3. 3.
    Frinken, V., Fischer, A., Manmatha, R., Bunke, H.: A novel word spotting method based on recurrent neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 211–224 (2011)Google Scholar
  4. 4.
    Von Zeddelmann, D., Kurth, F., Muller, M.: Perceptual audio features for unsupervised key-phrase detection. In: 2010 IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP, pp. 257–260 (2010)Google Scholar
  5. 5.
    Keshet, J., Grangier, D., Bengio, S.: Discriminative keyword spotting. Speech Communication, 317–329 (2009)Google Scholar
  6. 6.
    Jansen, A., Niyogi, P.: Point process models for spotting keywords in continuous speech. IEEE Transactions on Audio, Speech, and Language Processing 17(8), 1457–1470 (2009)CrossRefGoogle Scholar
  7. 7.
    Shao, J., Zhao, Q., Zhang, P., Liu, Z., Yan, Y.: A fast fuzzy keyword spotting algorithm based on syllable confusion network. In: Eighth Annual Conference of the International Speech Communication Association, pp. 2405–2408 (2007)Google Scholar
  8. 8.
    Ramachandran, R.P., Mammone, R.J.: Modern methods of speech processing, vol. 327. Springer (1995)Google Scholar
  9. 9.
    Christiansen, R., n, C.: Detecting and locating key words in continuous speech using linear predictive coding. IEEE Transactions on Acoustics, Speech and Signal Processing 25(5), 361–367 (1977)Google Scholar
  10. 10.
    Myers, C., Rabiner, L., Rosenberg, A.: An investigation of the use of dynamic time warping for word spotting and connected speech recognition. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1980, pp. 173–177. IEEE (1980)Google Scholar
  11. 11.
    Rohlicek, J.R., Russell, W., Roukos, S., Gish, H.: Continuous hidden markov modeling for speaker-independent word spotting. In: Acoustics, Speech, and Signal Processing 1989, pp. 627–630. IEEE (1989)Google Scholar
  12. 12.
    Wilpon, J., Rabiner, L., Lee, C., Goldman, E.: Automatic recognition of keywords in unconstrained speech using hidden markov models. IEEE Transactions on Acoustics, Speech and Signal Processing 38(11), 1870–1878 (1990)CrossRefGoogle Scholar
  13. 13.
    Weintraub, M.: Lvcsr log-likelihood ratio scoring for keyword spotting. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1995, pp. 297–300 (1995)Google Scholar
  14. 14.
    Szoke, I., Schwarz, P., Matejka, P., Burget, L., Karafiát, M., Fapso, M., Cernocky, J.: Comparison of keyword spotting approaches for informal continuous speech. In: Proc. of Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (2005)Google Scholar
  15. 15.
    Szöke, I., Schwarz, P., Matějka, P., Burget, L., Karafiát, M., Černocký, J.‘.: Phoneme based acoustics keyword spotting in informal continuous speech. In: Matoušek, V., Mautner, P., Pavelka, T. (eds.) TSD 2005. LNCS (LNAI), vol. 3658, pp. 302–309. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  16. 16.
    Laurinciukaite, S., Lipeika, A.: Syllable–phoneme based continuous speech recognition. Electronics and Electrical Engineering 6, 70 (2006)Google Scholar
  17. 17.
    Zhang, Y., Glass, J.R.: Unsupervised spoken keyword spotting via segmental dtw on gaussian posteriorgrams. In: Automatic Speech Recognition & Understanding, pp. 398–403. IEEE (2009)Google Scholar
  18. 18.
    Aradilla, G., Vepa, J., Bourlard, H.: Using posterior-based features in template matching for speech recognition. In: Int. Conf. on Spoken Language Processing (2006)Google Scholar
  19. 19.
    Park, A.S., Glass, J.R.: Unsupervised pattern discovery in speech, vol. 16, pp. 186–197. IEEE (2008)Google Scholar
  20. 20.
    Zhang, S., Shuang, Z., Shi, Q., Qin, Y.: Improved mandarin keyword spotting using confusion garbage model. In: 2010 20th International Conference on Pattern Recognition (ICPR), pp. 3700–3703. IEEE (2010)Google Scholar
  21. 21.
    Greibus, M., Telksnys, L.: Speech segmentation analysis using synthetic signals. In: Electronics and Electrical Engineering (2012)Google Scholar
  22. 22.
    Skripkauskas, M.: Lietuviu snekos signalu segmentavimas kvazifonemomis. In: Informacins Technologijos, pp. 76–81 (2006)Google Scholar
  23. 23.
    Horák, P.: Automatic speech segmentation based on alignment with a text-to-speech system. Improvements in Speech Synthesis, pp. 328–338. Wiley Online Library (2002)Google Scholar
  24. 24.
    Greibus, M., Telksnys, L.: Rule based speech signal segmentation. Journal of Telecommunications and Information Technology (JTIT) 1, 37–44 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mindaugas Greibus
    • 1
  • Laimutis Telksnys
    • 1
  1. 1.Vilnius University Institute of Mathematics and InformaticsVilniusLithuania

Personalised recommendations