🤖 AI Summary
To address the scarcity of research on isolated-word speech recognition for Bangla and the limited modeling capacity for low-resource languages, this paper introduces a speaker-independent bilingual speech dataset comprising Bangla and English, and proposes an end-to-end classification framework based on MFCC features and a 7-layer deep feedforward neural network (DFFNN). The method bypasses complex acoustic modeling and external linguistic resources, achieving 93.42% accuracy on a moderately sized multi-class dataset—significantly outperforming existing approaches. Key contributions include: (1) the first open-source bilingual (Bangla–English) benchmark dataset for isolated-word recognition; (2) empirical validation of lightweight DFFNNs for effective isolated-word recognition in low-resource languages; and (3) a reproducible, deployable technical pathway for speech recognition in resource-constrained languages.
📝 Abstract
As the most important human-machine interfacing tool, an insignificant amount of work has been carried out on Bangla Speech Recognition compared to the English language. Motivated by this, in this work, the performance of speaker-independent isolated speech recognition systems has been implemented and analyzed using a dataset that is created containing both isolated Bangla and English spoken words. An approach using the Mel Frequency Cepstral Coefficient (MFCC) and Deep Feed-Forward Fully Connected Neural Network (DFFNN) of 7 layers as a classifier is proposed in this work to recognize isolated spoken words. This work shows 93.42% recognition accuracy which is better compared to most of the works done previously on Bangla speech recognition considering the number of classes and dataset size.