A Discrete Wavelet Transform Based Approach to Hindi Speech Recognition

HMM Based Enhanced Dynamic Time Warping Model for Efficient Hindi Language Speech Recognition System

“…R K Agarwal et al [2] also presented a HMM with Gaussian mixture based automatic ASR using MFCC features, but this technique was also evaluated for simple utterances. Shivesh Ranjan [3] has also applied LPC over Discrete Wavelet transform coefficients for designing a speech recognition system for Hindi words, but it focuses over computing LPC coefficients separately for the wavelets coefficients. These authors focused on features extraction and matching techniques.…”

Hindi phoneme classification using Wiener filtered wavelet packet decomposed periodic and aperiodic acoustic feature

“…This type of problem was solved by considering WPs as the feature extraction technique [4][5][6]. WPs [4,[7][8][9] can efficiently be used to model the slowly varying quasi-periodic signal like speech signal. For this reason, WPs are widely used in the field of signal compression, detection and classification.…”

ASIC design of a phoneme recogniser based on discrete wavelet transforms and support vector machines

“…Various applications where ASR is, or can be employed, vary from simple tasks to more complex ones. Some of these include speech-to-text input, ticket reservations, air traffic control, security and biometric identification, gaming, home automation and automobile sectors [1] [2]. Additionally, disabled and elderly persons can highly benefit from advances in the field of ASR.…”