A
Astik Biswas
Researcher at Stellenbosch University
Publications - 41
Citations - 413
Astik Biswas is an academic researcher from Stellenbosch University. The author has contributed to research in topics: Language model & Wavelet. The author has an hindex of 11, co-authored 41 publications receiving 353 citations. Previous affiliations of Astik Biswas include National Institute of Technology, Rourkela & IMS Engineering College.
Papers
More filters
Journal ArticleDOI
Admissible wavelet packet features based on human inner ear frequency response for Hindi consonant recognition
TL;DR: A new filter structure using admissible wavelet packet analysis is proposed for Hindi phoneme recognition using a Hidden Markov Model (HMM) based classifier and shows better performance than conventional features for Hindi consonant recognition.
Robust Features for Connected Hindi Digits Recognition
TL;DR: In this article, robust features such as Revised Perceptual Linear Prediction (RPLP), Bark frequency cepstral coefficients (BFCC) and Mel frequency perceptual linear prediction (MF-PLP) are used for speaker-independent connected Hindi digits recognition in clean and noisy environments.
Posted Content
Spoken Language Identification Using Hybrid Feature Extraction Methods
TL;DR: This paper introduces and motivates the use of hybrid robust feature extraction technique for spoken language identification (LID) system and shows better identification rate using hybrid feature extraction techniques compared to conventional feature extraction methods.
Journal ArticleDOI
Feature extraction technique using ERB like wavelet sub-band periodic and aperiodic decomposition for TIMIT phoneme recognition
TL;DR: This frontend feature processing technique employs equivalent rectangular bandwidth (ERB) filter like wavelet speech feature extraction method called Wavelet ERB Sub-band based Periodicity and Aperiodicity Decomposition (WERB-SPADE), and examines its validity for TIMIT phone recognition task in noisy environments.
Journal ArticleDOI
Multiple cameras audio visual speech recognition using active appearance model visual features in car environment
TL;DR: The shape and appearance information are extracted from jaw and lip region to enhance the performance in vehicle environments to show more robustness compared to acoustic speech recognizer across all driving conditions.