Abstract
Dynamic speech properties, such as time warping, silence removal and background noise reduction are the most challenging issues in continuous speech signal matching. Among all of them, the time warped speech signal matching is of great interest and has been a tough challenge for the researchers. The literature contains a variety of techniques to measure the similarity between speech utterances, however there are some limitations associated with these techniques. This paper introduces an adaptive framing based continuous speech tracking and similarity measurement approach that uses a Kalman filter (KF) as a robust tracker. The use of KF is novel for time warped speech signal matching and dynamic time warping. A dynamic state model is presented based on equations of linear motion. In this model, fixed length frame of input (test) speech signal is considered as a unidirectional moving object by sliding it along the template speech signal. The best matched position estimate in template speech (sample number) for corresponding test frame at current time is calculated. Simultaneously, another position observation is produced by a feature based distance metric. The position estimated by the state model is fused with the observation using KF along with the noise variances. The best estimated frame position in the template speech for the current state is calculated. Finally, forecasting of the noise variances and template frame size for next state are made according to the KF output. The experimental results demonstrate the robustness of the proposed technique in terms of time warped speech signal matching as well as in computation cost.
Similar content being viewed by others
References
Amin, S., Gholam, A., & Amir, S. (2009). Speech recognition from PSD using neural network. International MultiConference of Engineers and Computer Scientists, I, 174.
Antanas, L. (2010). Optimization of formant feature based speech recognition. Institute of Mathematics and Informatics, Informatica, 21(3), 361–374.
Arthur, G. (1974). Applied optimal estimation (pp. 72–79). Cambridge: MIT Press.
Bob, L. (2009). Fundamentals of real time spectrum analysis. USA: Tektronix Primer.
Bolls, S. F. (2003). Suppression of acoustic noise in speech using spectral subtraction. IEEE Transactions on Acoustics, Speech, and Signal Processing, 27(2), 113–120.
Chotirat, R., & Eamonn, K. (2005). Three Myths about dynamic time warping data mining. In the Proceedings of SIAM International Conference on Data Mining (pp. 506–510).
Dave, N. (2013). Feature extraction methods LPC, PLP and MFCC. Speech Recognition. International Journal for Advance Research in Engineering and Technology, 1(6), 1–4.
Dhingra, S., Nijhawan, G., & Pandit, P. (2013). Isolated speech recognition using MFCC and DTW. International Journal Advanced Research in Electrical Electronics and Instrumentation Engineering, 2(8), 1–8.
Festvox. CMU Arctic Databases. Accessed January 13, 2013, from http://www.festvox.org/cmu_arctic/index.html.
Gannot, S., Burshtien, D., & Weinstein, E. (2002). Iterative and sequential Kalman filter-based speech enhancement algorithms. IEEE Transactions, Speech and Audio Processing, 6(4), 373–385.
Giannakopoulos, T. (2014). A method for silence removal and segmentation of speech signals, implemented in Matlab. Accessed May, 13, 2014 from http://cgi.di.uoa.gr/~tyiannak/Software.html.
Gibson, D., Boneung, K., & Gray, S. D. (1989). Filtering of coloured noise for speech enhancement and coding. In International Conference on Acoustics, Speech and Signal Processing (Vol. 1, pp. 349–352).
Greg, W., & Gary, B. (2006). An introduction to Kalman filter. TR 95- 041, Course 8, Chapel Hill, NC: University of North Carolina.
Hung, H., & Chittaranjan, G. (2010). The Idiap Wolf Corpus: Exploring group behaviour in a competitive role-playing game. Florence, Italy: ACM Multimedia.
Lalkhen, A. G., & McCluskey, A. (2008). Clinical tests: Sensitivity and specificity. Continuing Education in Anaesthesia, Critical Care & Pain, 8(6), 221–223.
Lawrence, R. R., Jay, G. W., & Frank, K. S. (1989). High performance connected digit recognition using Hidden Markov Models. IEEE Transactions on Acoustics, Speech and Signal Processing, 37(8), 1214–1225.
Lipman, R., Martin, & E., Paul. B. (1987). Multi-style training for robust isolated-word speech recognition. In IEEE International Conference of Acoustic, Speech, Signal Processing (pp. 705–708).
McCool, C., Marcel, S., Hadid, A., Pietikäinen, M., Matějka, P., Černocký, J., Poh, N., Kittler, J., Larcher, A., Lévy, C., Matrouf, D., Bonastre, J., Tresadern, P., & Cootes, T. (2012). Bi-Modal person recognition on a mobile phone: Using mobile phone data. In IEEE ICME Workshop on Hot Topics in Mobile Multimedia.
Melvyn, H., & Claude, L. (1988). Speaker dependent and independent speech recognition experiments with an auditory model. In International Conference on Acoustic Speech and Signal Processing (Vol. 1, pp. 215–218).
Michael, E. (2001). ‘Top 100 speeches’, American Rhetoric. Accessed December 12 2013 from http://www.americanrhetoric.com/top100speechesall.html
Mohinder, S. G., & Angus, A. (2001). Kalman filtering theory and practice using MATLAB (2nd ed., pp. 15–17). Canada: Wiley.
Nortel, N. (2002). Voice fundamentals: From analogue to ATM (pp. 1–4). Mississauga, ON: Nortel Networks Corporation.
Olivier, S. (1995). On the robustness of linear discriminant analysis as a pre-processing step for noisy speech recognition. In International Conference on Acoustics, Speech, and Signal Processing (Vol. 1, pp. 125–128).
Online Audio Stories, ‘short stories and audio books online for kids’. Accessed February, 01, 2014 from http://www.onlineaudiostories.com/category/all_stories/audio_stories/.
Pour, M. M., & Farokhi, F. (2009). An advanced method for speech recognition. International Scholarly and Scientific Research & Innovation, 3(1), 840–845.
Rabiner, L. (1989). A tutorial on Hidden Markov Models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286.
Ravindran, G., Shenbagadevi, S., & Salai, S. V. (2010). Cepstral and linear prediction techniques for improving intelligibility and audibility of impaired speech. Journal of Biomedical Science and Engineering, 3(1), 85–94.
Schmid, P., & Barnard, E. (1995). Robust, N-Best formant tracking. In Proceedings of EUROSPEECH’95 (pp. 737–740).
Sharma, P., & Rajpoot, A. K. (2013). Automatic identification of silence, unvoiced and voiced chunks in speech. Journal of Computer Science & Information Technology (CS & IT), 3(5), 87–96.
Xuedong, H., & Kai, L. (1993). On speaker-independent, speaker-dependent and speaker-adaptive speech recognition. IEEE Transactions on Speech and Audio Processing, 1(2), 150–157.
Yegnanarayana, B., & Sreekumar, T. (1984). Signal dependent matching for isolated word speech recognition system. Signal Processing, 7(2), 161–173.
Zahorian, S. A., & Hu, H. (2008). A spectral/temporal method for robust fundamental frequency tracking. Journal of Acoustic Society of America, 123(6), 4559–4571.
Author information
Authors and Affiliations
Corresponding author
Additional information
Rob Holton is a Head of Computer Science in University of Bradford
Rights and permissions
About this article
Cite this article
Khan, W., Holton, R. Time warped continuous speech signal matching using Kalman filter. Int J Speech Technol 18, 419–431 (2015). https://doi.org/10.1007/s10772-015-9277-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10772-015-9277-5