In this paper we will use different feature extraction approach in order to compare the stability of the Automatic Speech Recognition (ASR) on different SNR noise, in different situations. By using the classic feature extraction like: Mel filter Bank, Fast Fourier Transformation (FFT), Discrete Fourier Transformation (DFT). After we implement this methods for the different situations then we will warp the frequency of this methods directly on the spectrum in order to see if we get better results. The results will be compared with one another using the Word Error Rate algorithm (WER).
- Automatic Speech Recognition Samudravijaya K Tata Institute of Fundamental Research, Homi Bhabha Road, Mumbai 400005
- Piccone, J. (1992) Signal Modelling Techniques in Speech Recognition. Texas Instruments Shrawankar, U., Thakare, V. (2013) Techniques for feature extraction in speech recognition system: a comparative study.
- Bilmes, J. (2004). “What HMMs can’t do,” in Proceedings of the Institute of Electronics, Information and Communication Engineers Beyond HMM Workshop, Kyoto, Japan, Vol. 104, SP2004-81-95.
- Çetin, O., Kantor, A., King, S., Bartels, C., Magimai-Doss, M., Frankel, J., and Livescu, K. (2007). “An articulatory feature-based tandem approach and factored observation modeling,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2007)
- T. Wesker, B. Meyer, K. Wagener, J. Anem¨uller, A. Mertins, and B. Kollmeier. Oldenburg logatome speech corpus (OLLO) for speech recognition experiments with humans and machines. In Proc. of Interspeech, pages 1273–1276, Lisboa, Portugal, September 2005.
- G. Zhou, M.E. Deisher, and S. Sharma. Causal analysis of speech recognition failure in adverse environments. In Proc. of ICASSP, volume 4, pages 3816–1819, Orlando, Florida, May 2002.