• Mohit Kumar Goel

Recent studies have been focusing upon the performance of the speech recognition systems. The performance of robust speech-recognition system is measured in terms of accuracy of identification, computational cost and calculation speed. In speech recognition process, feature extraction is of utmost importance. Therefore, in this context, a feature extraction technique i.e. MFCCs has been discussed. Based on this, a technique has been proposed which combines conventional MFCC technique with Laplacian Eigenmaps. This proposed technique leads to dimensionality reduction of the feature matrix obtained by MFCC method, thus improving the performance system in terms of computational cost.

Speech recognition, MFCC, Laplacian Eigenmaps, Feature extraction, dimension reduction.

"A Novel Techniques for speech recognition using modified MFCC", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.627-632, November 2018, Available :http://www.jetir.org/papers/JETIRDR06093.pdf

"A Novel Techniques for speech recognition using modified MFCC", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp627-632, November 2018, Available at : http://www.jetir.org/papers/JETIRDR06093.pdf