Dynamic Time Warping Assisted SVM Classifier for Bangla Speech Recognition
Published in 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), 2018
This paper presents a Bangla speech recognition system that leverages Dynamic Time Warping (DTW) to align variable-length speech feature sequences and feeds the aligned representations to a Support Vector Machine (SVM) classifier. The approach addresses the temporal variability in spoken Bangla words and achieves competitive recognition accuracy on a curated dataset of Bangla speech samples.
Recommended citation: M. M. Rahman, D. R. Dipta and M. M. Hasan, "Dynamic Time Warping Assisted SVM Classifier for Bangla Speech Recognition," 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh, 2018.