A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918357551284224 |
|---|---|
| author | Ishmam, Zarif Mahir, Zarif Wasif, Shafnan Moin, Md. Ishtiak |
| author_facet | Ishmam, Zarif Mahir, Zarif Wasif, Shafnan Moin, Md. Ishtiak |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22935 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment Ishmam, Zarif Mahir, Zarif Wasif, Shafnan Moin, Md. Ishtiak Sound Artificial Intelligence 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. |
| title | A Holistic Framework for Robust Bangla ASR and Speaker Diarization with Optimized VAD and CTC Alignment |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2602.22935 |