Abstract
In this paper, we developed soft computing models for on-line automatic speech recognition (ASR) based on Bayesian on-line inference techniques.Bayesian on-line inference for change point detection (BOCPD) is tested for on-line environmental learning using highly non-stationary noisy speech samples from the Aurora2 speech database. Significant improvement in predicting and adapting to new acoustic conditions is obtained for highly non-stationary noises. The simulation results show that the Bayesian on-line inference-based soft computing approach would be one of the possible solutions to on-line ASR for real-time applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Acero, A.: Acoustical and environmental robustness in automatic speech recognition. Kluwer Academic Publisher, Massachussets (1993)
Adams, R.P., MacKay, D.J.C.: Bayesian on-line changepoint detection. University of Cambridge Technical Report arXiv:0710.3742v1[stat.ML] (2007)
Chowdhury, M.F.R., Selouani, S.-A., O’Shaughnessy, D.: Bayesian On-Line Change Point Detection Approach For Rapid Adaptation of Highly Non-Stationary Noise Tracking Algorithm. Submitted for: IEEE Int. Conf. Acoustics,Speech, Signal Proc. 2011 (2010)
Cohen, I.: Noise Estimation by Minima Controlled Recursive Averaging for Robust Speech Enhancement. IEEE Signal Processing Letters 9(1), 12–15 (2002)
Cohen, I.: Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Trans. Audio, Speech, Signal Proc. 2(5), 466–475 (2003)
Fan, N.: Speech noise estimation using enhanced minima controlled recursive averaging. In: Proc. IEEE Int. Conf. Acoustics, Speech, Signal Proc., vol. 4, pp. 581–584 (2007)
Hirsch, H.-G., Pearce, D.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: Proceedings of ISCA ITRW ASR2000 Automatic Speech Recognition: Challenges for the Next Millennium, pp. 181–188 (2000)
Li, J., Deng, L., Yu, D., et al.: A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions. Computer Speech and Language 23, 389–405 (2009)
O’Shaughnessy, D.: Speech Communications: Human and Machine. Wiley-IEEE Press (2000)
Rangachari, S., Loizou, P.: A noise estimation algorithm for highly nonstationary environments. Speech Communication 28, 220–231 (2006)
Turner, R.: Bayesian Change Point Detection for Satellite Fault Prediction. In: Proceedings of Interdisciplinary Graduate Conference (IGC), Cambridge, UK, pp. 213–221 (2010)
Young S.: ATK An Application Toolkit for HTK. Machine Intelligence Laboratory, Cambridge University Engineering Dept, Cambridge, UK (2007), http://www.mi.eng.cam.ac.uk/research/dialogue/ATK_Manual.pdf (cited June 2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chowdhury, M.F.R., Selouani, SA., O’Shaughnessy, D. (2011). Real-Time Bayesian Inference: A Soft Computing Approach to Environmental Learning for On-Line Robust Automatic Speech Recognition. In: Corchado, E., Snášel, V., Sedano, J., Hassanien, A.E., Calvo, J.L., Ślȩzak, D. (eds) Soft Computing Models in Industrial and Environmental Applications, 6th International Conference SOCO 2011. Advances in Intelligent and Soft Computing, vol 87. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19644-7_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-19644-7_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19643-0
Online ISBN: 978-3-642-19644-7
eBook Packages: EngineeringEngineering (R0)