MLC-SLM挑战赛中的BUT系统

摘要

我们提出了一种双说话人自动语音识别（ASR）系统，该系统结合了DiCoW——一种基于Whisper的说话人日志条件变体——与DiariZen，一种构建在Pyannote之上的说话人日志处理流程。首先，我们在无需微调的情况下，评估了这两种系统在跨领域（OOD）多语言场景中的表现。在此场景下，DiariZen持续超越基线Pyannote说话人日志模型，展现了强大的泛化能力。尽管DiCoW仅针对目标说话人ASR在英语数据上进行了微调，它仍保持了稳健的多语言性能，表明编码器修改保留了Whisper的多语言能力。随后，我们在MLC-SLM挑战赛数据上对DiCoW和DiariZen进行了微调。微调后的DiariZen继续优于微调的Pyannote基线，而DiCoW则通过领域适应获得了进一步的提升。我们的最终系统在MLC-SLM挑战赛任务2中实现了16.75%的微平均tcpWER/CER，并位列第二。最后，我们识别出训练数据中的若干标注不一致问题——如缺失的语音片段和错误的静音标注——这些问题可能阻碍说话人日志的微调。我们提出了简单的缓解策略以解决这些问题，并提升系统的鲁棒性。

English

We present a two-speaker automatic speech recognition (ASR) system that combines DiCoW -- a diarization-conditioned variant of Whisper -- with DiariZen, a diarization pipeline built on top of Pyannote. We first evaluate both systems in out-of-domain (OOD) multilingual scenarios without any fine-tuning. In this scenario, DiariZen consistently outperforms the baseline Pyannote diarization model, demonstrating strong generalization. Despite being fine-tuned on English-only data for target-speaker ASR, DiCoW retains solid multilingual performance, indicating that encoder modifications preserve Whisper's multilingual capabilities. We then fine-tune both DiCoW and DiariZen on the MLC-SLM challenge data. The fine-tuned DiariZen continues to outperform the fine-tuned Pyannote baseline, while DiCoW sees further gains from domain adaptation. Our final system achieves a micro-average tcpWER/CER of 16.75% and ranks second in Task 2 of the MLC-SLM challenge. Lastly, we identify several labeling inconsistencies in the training data -- such as missing speech segments and incorrect silence annotations -- which can hinder diarization fine-tuning. We propose simple mitigation strategies to address these issues and improve system robustness.

MLC-SLM挑战赛中的BUT系统

BUT System for the MLC-SLM Challenge

摘要

Support