Research

Paper

AI LLM March 03, 2026

An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization

Authors

Epshita Jahan, Khandoker Md Tanjinul Islam, Pritom Biswas, Tafsir Al Nafin

Abstract

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

Metadata

arXiv ID: 2603.03158
Provider: ARXIV
Primary Category: cs.SD
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03158v1</id>\n    <title>An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization</title>\n    <updated>2026-03-03T17:00:42Z</updated>\n    <link href='https://arxiv.org/abs/2603.03158v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03158v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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\n  Index Terms: Bengali speech recognition, speaker diarization, Whisper, ASR, low-resource languages, pyannote, voice activity detection</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SD'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-03T17:00:42Z</published>\n    <arxiv:comment>5 pages, 2 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.SD'/>\n    <author>\n      <name>Epshita Jahan</name>\n    </author>\n    <author>\n      <name>Khandoker Md Tanjinul Islam</name>\n    </author>\n    <author>\n      <name>Pritom Biswas</name>\n    </author>\n    <author>\n      <name>Tafsir Al Nafin</name>\n    </author>\n  </entry>"
}