针对低资源孟加拉语语音，实现高精度长音频识别与说话人分离。
Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
- 用细调的Whisper模型结合声源分离技术提升识别准确率。
- 语音识别WER低至0.361，说话人分离DER低至0.209。
- 适合关注小语种语音处理或多语言场景的研究者。
我们提交了端到端的孟加拉语长语音识别（ASR）与说话人分离系统至Kaggle的DL Sprint 4.0竞赛。孟加拉语在发音音素丰富、方言差异大、频繁夹杂英语及标注数据稀缺方面带来显著挑战。对于语音识别，采用经BengaliAI微调的Whisper medium模型，结合Demucs声源分离、静音边界分块和精细调参，取得私有测试集最优词错误率（WER）0.37738，公开测试集0.36137。对于说话人分离，将pyannote.audio默认分割模型替换为孟加拉语微调版本，搭配wespeaker-voxceleb-resnet34-LM嵌入与基于质心的层次聚类，达到私有测试集最佳分离错误率（DER）0.27671，公开测试集0.20936。实验表明，领域专用的分割模块微调、声源分离及自然静音感知分块是低资源孟加拉语语音处理中最关键的设计选择。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。