Admissible wavelet packet sub‐band‐based harmonic energy features for Hindi phoneme recognition

2015 ◽  
Vol 9 (6) ◽  
pp. 511-519 ◽  
Author(s):  
Astik Biswas ◽  
Prasanna Kumar Sahu ◽  
Anirban Bhowmick ◽  
Mahesh Chandra
Keyword(s):  
Wavelet Packet ◽  
Phoneme Recognition ◽  
Admissible Wavelet

WAVELET SUB-BAND BASED TEMPORAL FEATURES FOR ROBUST HINDI PHONEME RECOGNITION

2010 ◽  
Vol 08 (06) ◽  
pp. 847-859 ◽  
Author(s):  
O. FAROOQ ◽  
S. DATTA ◽  
M. C. SHROTRIYA
Keyword(s):  
Recognition Performance ◽  
Wavelet Packet ◽  
Phoneme Recognition ◽  
Linear Discriminant ◽  
Temporal Features ◽  
Admissible Wavelet ◽  
Different Types ◽  
Noisy Background ◽  
Frequency Band Energy ◽  
Feature Extraction Technique

This paper proposes the use of wavelet transform-based feature extraction technique for Hindi speech recognition application. The new proposed features take into account temporal as well as frequency band energy variations for the task of Hindi phoneme recognition. The recognition performance achieved by the proposed features is compared with the standard MFCC and 24-band admissible wavelet packet-based features using a linear discriminant function based classifier. To evaluate robustness of these features, the NOISEX database is used to add different types of noise into phonemes to achieve signal-to-noise ratios in the range of 20 dB to -5 dB. The recognition results show that under noisy background the proposed technique always achieves a better performance over MFCC-based features.

scholarly journals Auditory ERB like admissible wavelet packet features for TIMIT phoneme recognition

2014 ◽  
Vol 17 (3) ◽  
pp. 145-151 ◽  
Author(s):  
P.K. Sahu ◽  
Astik Biswas ◽  
Anirban Bhowmick ◽  
Mahesh Chandra
Keyword(s):  
Wavelet Packet ◽  
Phoneme Recognition ◽  
Admissible Wavelet

EVALUATION OF A WAVELET BASED ASR FRONT-END

2007 ◽  
Vol 05 (04) ◽  
pp. 641-654 ◽  
Author(s):  
OMAR FAROOQ ◽  
SEKHARJIT DATTA
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Recognition Performance ◽  
Wavelet Packet ◽  
Additive White Gaussian Noise ◽  
Discrete Wavelet ◽  
Mel Frequency Cepstral Coefficients ◽  
Admissible Wavelet ◽  
Transform Coefficients ◽  
Short Time

In this paper, we propose the use of the wavelet transform for the extraction of features for phonemes in order to overcome some of the shortcomings of short time Fourier transform. New log-energy based features are proposed using discrete wavelet transform as well as wavelet packets and their recognition performance has been evaluated. These features overcome the problem of shift variance as encountered in the features based on the discrete wavelet transform coefficients. The effect on the recognition performance by choosing different mother wavelets for the decomposition and window duration is also studied. Finally, a scheme based on the admissible wavelet packet has also been proposed and the results are discussed and compared with the frequently used Mel Frequency Cepstral Coefficients based features. The recognition performance of these features is further evaluated in the presence of different level of additive white Gaussian noise.

Sign in / Sign up

Export Citation Format

Share Document