Authors: Aditya Sharma, M.C. Shrotriya, Omar Farooq, Z.A. Abbasi
Addresses: Department of Electronics Engineering, AMU, Aligarh, India. ' Department of Electronics and Communication Engineering, Birla Institute of Technology, Mesra, Ranchi, Jharkhand – 835215, India. ' Department of Electronics Engineering, AMU, Aligarh, India. ' Department of Electronics Engineering, AMU, Aligarh, India
Abstract: Hybrid features are presented for speech recognition that uses linear prediction in combination with multi-resolution capabilities of wavelet transform. Wavelet-Based Linear Prediction Coefficients (WBLPC) are obtained by applying 3 and 4-level wavelet decomposition and then having linear prediction of each sub-bands to get total 13 features. These features have been tested using a linear discriminant function and Hidden Markov Model (HMM) based classifier for speaker dependent and independent isolated Hindi digits recognition. 3-level WBLPC features gave higher percentage recognition than LPC features while 4-level WBLPC features using HMM gave the highest percentage recognition for both speaker dependent and independent cases.
Keywords: hybrid features; wavelet transform; Hindi digits recognition; linear discriminant analyser; HMM; hidden Markov model; speech recognition; linear prediction coefficients; LPC.
International Journal of Information and Communication Technology, 2008 Vol.1 No.3/4, pp.373 - 381
Published online: 23 Mar 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article