A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment
This work provides a scalable solution for real-world, long-form Bangla speech applications, particularly in complex, multi-speaker environments, addressing a performance gap for this low-resource language.
The paper addresses the challenge of Automatic Speech Recognition (ASR) and Speaker Diarization for long-form Bangla audio, which typically struggles beyond 30-60 seconds. It proposes a framework that optimizes Voice Activity Detection (VAD) and uses Connectionist Temporal Classification (CTC) segmentation with forced word alignment to maintain accuracy over extended durations.
Despite being one of the most widely spoken languages globally, Bangla remains a low-resource language in the field of Natural Language Processing (NLP). Mainstream Automatic Speech Recognition (ASR) and Speaker Diarization systems for Bangla struggles when processing longform audio exceeding 3060 seconds. This paper presents a robust framework specifically engineered for extended Bangla content by leveraging preexisting models enhanced with novel optimization pipelines for the DL Sprint 4.0 contest. Our approach utilizes Voice Activity Detection (VAD) optimization and Connectionist Temporal Classification (CTC) segmentation via forced word alignment to maintain temporal accuracy and transcription integrity over long durations. Additionally, we employed several finetuning techniques and preprocessed the data using augmentation techniques and noise removal. By bridging the performance gap in complex, multi-speaker environments, this work provides a scalable solution for real-world, longform Bangla speech applications.