# Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization

arXiv: https://arxiv.org/abs/2602.21741 · HTML: https://mlsanity.com/paper/2602.21741/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Powerset multi-class cross entropy loss for neural speaker diarization](https://mlsanity.com/paper/2310.13025/) (2023)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [Speaker Diarization with LSTM](https://mlsanity.com/paper/1710.10468/) (2017)
- [Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization](https://mlsanity.com/paper/2602.14291/) (2026)

## Abstract (arXiv)

We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme inventory, significant dialectal variation, frequent code-mixing with English, and a relative scarcity of large-scale labelled corpora. For ASR we achieve a best private Word Error Rate (WER) of 0.37738 and public WER of 0.36137, combining a BengaliAI fine-tuned Whisper medium model with Demucs source separation for vocal isolation, silence-boundary chunking, and carefully tuned generation hyperparameters. For speaker diarization we reach a best private Diarization Error Rate (DER) of 0.27671 and public DER of 0.20936 by replacing the default segmentation model inside the pyannote.audio pipeline with a Bengali-fine-tuned variant, pairing it with wespeaker-voxceleb-resnet34-LM embeddings and centroid-based agglomerative clustering. Our experiments demonstrate that domain-specific fine-tuning of the segmentation component, vocal source separation, and natural silence-aware chunking are the three most impactful design choices for low-resource Bengali speech processing.