An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918367855640576 |
|---|---|
| author | Jahan, Epshita Islam, Khandoker Md Tanjinul Biswas, Pritom Nafin, Tafsir Al |
| author_facet | Jahan, Epshita Islam, Khandoker Md Tanjinul Biswas, Pritom Nafin, Tafsir Al |
| contents | Bengali remains a low-resource language in speech technology, especially for complex tasks like long-form transcription and speaker diarization. This paper presents a multistage approach developed for the "DL Sprint 4.0 - Bengali Long-Form Speech Recognition" and "DL Sprint 4.0 - Bengali Speaker Diarization" competitions on Kaggle, addressing the challenge of "who spoke when/what" in hour-long recordings. We implemented Whisper Medium fine-tuned on Bengali data (bengaliAI/tugstugi bengaliai-asr whisper-medium) for transcription and integrated pyannote/speaker-diarization-community-1 with our custom-trained segmentation model to handle diverse and noisy acoustic environments. Using a two-pass method with hyperparameter tuning, we achieved a DER of 0.27 on the private leaderboard and 0.19 on the public leaderboard. For transcription, chunking, background noise cleaning, and algorithmic post-processing yielded a WER of 0.38 on the private leaderboard. These results show that targeted tuning and strategic data utilization can significantly improve AI inclusivity for South Asian languages. All relevant code is available at: https://github.com/Short-Potatoes/Bengali-long-form-transcription-and-diarization.git
Index Terms: Bengali speech recognition, speaker diarization, Whisper, ASR, low-resource languages, pyannote, voice activity detection |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03158 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization Jahan, Epshita Islam, Khandoker Md Tanjinul Biswas, Pritom Nafin, Tafsir Al Sound Artificial Intelligence Bengali remains a low-resource language in speech technology, especially for complex tasks like long-form transcription and speaker diarization. This paper presents a multistage approach developed for the "DL Sprint 4.0 - Bengali Long-Form Speech Recognition" and "DL Sprint 4.0 - Bengali Speaker Diarization" competitions on Kaggle, addressing the challenge of "who spoke when/what" in hour-long recordings. We implemented Whisper Medium fine-tuned on Bengali data (bengaliAI/tugstugi bengaliai-asr whisper-medium) for transcription and integrated pyannote/speaker-diarization-community-1 with our custom-trained segmentation model to handle diverse and noisy acoustic environments. Using a two-pass method with hyperparameter tuning, we achieved a DER of 0.27 on the private leaderboard and 0.19 on the public leaderboard. For transcription, chunking, background noise cleaning, and algorithmic post-processing yielded a WER of 0.38 on the private leaderboard. These results show that targeted tuning and strategic data utilization can significantly improve AI inclusivity for South Asian languages. All relevant code is available at: https://github.com/Short-Potatoes/Bengali-long-form-transcription-and-diarization.git Index Terms: Bengali speech recognition, speaker diarization, Whisper, ASR, low-resource languages, pyannote, voice activity detection |
| title | An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2603.03158 |