Research ArticleOpen AccessGoogle Scholar indexed
Sudden Noise Reduction Based on GMM with Noise Power Estimation
Graduate School of Engineering, Kobe University, Kobe, Japan.
Graduate School of Engineering, Kobe University, Kobe, Japan.
Graduate School of Engineering, Kobe University, Kobe, Japan.
- 1 Graduate School of Engineering, Kobe University, Kobe, Japan.
- 2 Graduate School of Engineering, Kobe University, Kobe, Japan.
- 3 Graduate School of Engineering, Kobe University, Kobe, Japan.
Journal of Software Engineering and Applications·Volume 03 (2010)·Pages 341–346·Published 30 April 2010·DOI10.4236/jsea.2010.34039
Copy link · social · email
Abstract
This paper describes a method for reducing sudden noise using noise detection and classification methods, and noise power estimation. Sudden noise detection and classification have been dealt with in our previous study. In this paper, GMM-based noise reduction is performed using the detection and classification results. As a result of classification, we can determine the kind of noise we are dealing with, but the power is unknown. In this paper, this problem is solved by combining an estimation of noise power with the noise reduction method. In our experiments, the proposed method achieved good performance for recognition of utterances overlapped by sudden noises.
KeywordsSudden NoiseModel-Based Noise ReductionSpeech Recognition
- M. Fujimoto, et al., “Particle Filter Based Non-Stationary Noise Tracking for Robust Speech Recognition,” Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2005, pp. 257-260.
- M. Kotta, et al., “Speech Enhancement in Non-Stationary Noise Environments Using Noise Properties,” Speech Communication, Vol. 48, No. 11, 2006, pp. 96-109.
- T. Jitsuhiro, et al., “Robust Speech Recognition Using Noise Suppression Based on Multiple Composite Models and Multi-Pass Search,” Proceedings of Automatic Speech Recognition and Understanding (ASRU), 2007, pp. 53-58.
- T. Hirai, S. Kuroiwa, S. Tsuge, F. Ren, M. A. Fattah, “A Speech Emphasis Method for Noise-Robust Speech Recognition by Using Repetitive Phrase,” Proceedings of International Conference on Chemical Thermodynamics (ICCT), 2006, pp. 1-4.
- P. J. Moreno, B. Raj and R. M. Stern, “A Vector Taylor Series Approach for Environment Independent Speech Recognition,” Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1996, pp. 733-736.
- J. C. Segura, et al., “Model-Based Compensation of the Additive Noise for Continuous Speech Recognition. Experiments Using the AURORA II Database and Tasks,” Proceedings of Eurospeech, 2001, pp. 221-224.
- L. Deng, et al., “Enhancement of Log Mel Power Spectra of Speech Using a Phase-Sensitive Model of the Acoustic Environment and Sequential Estimation of the Corrupting Noise,” IEEE Transactions on Speech and Audio Pro- cessing, Vol. 12, 2004, pp. 133-143.
- N. Miyake, T. Takiguchi and Y. Ariki, “Noise Detection and Classification in Speech Signals with Boosting,” IEEE Workshop on Statistical Signal Processing (SSP), 2007, pp. 778-782.
- Y. Freund, et al., “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” Journal of Computer and System Sciences, Vol. 55, 1997, pp. 119-139.
- S. Nakamura, et al., “Acoustical Sound Database in Real Environments for Sound Scene Understanding and Hands-Free Speech Recognition,” Proceedings of 2nd ICLRE, 2000, pp. 965-968.