Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment

TL;DR

This paper presents a comprehensive Bengali speech dataset and optimized methods for long-form speech recognition and speaker diarization, emphasizing data augmentation, fine-tuning, and heuristic post-processing to improve performance in low-resource settings.

Contribution

It introduces the Lipi-Ghor-882 dataset and demonstrates that targeted fine-tuning and heuristic post-processing significantly enhance long-form Bengali ASR and diarization.

Findings

Targeted fine-tuning with aligned annotations improves ASR accuracy.

Heuristic post-processing boosts speaker diarization performance.

Achieved a low 0.019 RTF for real-time processing.

Abstract

Although Automatic Speech Recognition (ASR) in Bengali has seen significant progress, processing long-duration audio and performing robust speaker diarization remain critical research gaps. To address the severe scarcity of joint ASR and diarization resources for this language, we introduce Lipi-Ghor-882, a comprehensive 882-hour multi-speaker Bengali dataset. In this paper, detailing our submission to the DL Sprint 4.0 competition, we systematically evaluate various architectures and approaches for long-form Bengali speech. For ASR, we demonstrate that raw data scaling is ineffective; instead, targeted fine-tuning utilizing perfectly aligned annotations paired with synthetic acoustic degradation (noise and reverberation) emerges as the singular most effective approach. Conversely, for speaker diarization, we observed that global open-source state-of-the-art models (such as Diarizen) performed surprisingly poorly on this complex dataset. Extensive model retraining yielded negligible improvements; instead, strategic, heuristic post-processing of baseline model outputs proved to be the primary driver for increasing accuracy. Ultimately, this work outlines a highly optimized dual pipeline achieving a $\sim$0.019 Real-Time Factor (RTF), establishing a practical, empirically backed benchmark for low-resource, long-form speech processing.