collaborators

1 paper

cs.CL2026

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

Md. Nazmus Sakib, Shafiul Tanvir, Mesbah Uddin Ahamed +1

Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our…