AI RESEARCH

ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization

arXiv CS.CL

ArXi:2603.19256v1 Announce Type: new Bengali is spoken by over 230M people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech Recognition (Task~1) and Bengali Speaker Diarization Challenge (Task~2). For Task~1, we propose a data-centric pipeline that constructs a high-quality