为高性能多语言ASR添加鲁棒的代码切换能力
Adding Robust Code-Switching Capabilities to High Performance Multilingual ASR
AI总结：
针对多语言ASR系统中代码切换的挑战，提出贝叶斯因子化适应方法，在不降低单语性能的前提下，通过少量合成数据将切换相关知识高效集成到预训练模型中，使代码切换词转录错误降低32.87%，整体WER改善5.31%。
摘要：
代码切换（CSW）对于实际部署中的大型多语言ASR系统仍然具有挑战性。虽然可以在合成CSW数据上进行微调，但这通常会降低强大的单语基线性能。我们的目标是在扩展模型以处理复杂代码切换（包括跨语言的形态变化）的同时，保持这些能力。我们提出了贝叶斯因子化适应，它学习将切换相关知识高效集成到强大的预训练模型中，而不会覆盖现有能力。我们的方法仅需少量合成数据，即可将代码切换词的转录错误降低32.87%，同时整体WER改善5.31%，且保持单语性能不变。我们的结果表明，有效的CSW适应更多地依赖于知识集成而非数据复杂性。
英文摘要：
Code-switching (CSW) remains challenging for large multi-lingual ASR systems in real-world deployment. While fine-tuning on synthetic CSW data is possible, it generally degrades strong monolingual baselines. Our goal is to preserve these capabilities while extending models to handle complex code-switching, including morphological variations across languages. We propose Bayesian factorized adaptation, which learns to efficiently integrate switching-relevant knowledge into strong pretrained models without overwriting existing capabilities. Requiring only a small amount of synthetic data, our approach reduces transcription errors by 32.87% on code-switched words while improving overall WER by 5.31%, all while maintaining mono-lingual performance. Our results demonstrate that effective CSW adaptation depends more on knowledge integration than data complexity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
