用语言相似性提升濒危语种语音识别效果
Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR
- 融合声学与语言特征，筛选适合迁移的高资源语言
- 印地语和阿萨姆语使错误率显著降低
- 声学相似性最影响微调效果，音素与语法相似性影响零样本迁移
本文研究语言相似性如何提升极低资源环境下自动语音识别（ASR）的跨语言迁移效果。以澳大利亚原住民语言瓦尔皮里语为例，其标注语音数据极少，依赖迁移学习至关重要。我们提出一个框架，结合预训练语音模型的声学相似性与基于语言类型、音素库、语法和句法特征的语言相似性，对高资源源语言进行排序并评估其向瓦尔皮里语迁移的有效性。实验使用Whisper模型表明，声学与语言类型相似的语言在迁移中表现优于单语和多语基线。阿萨姆语和印地语在词错误率和字符错误率上均有显著下降。相关性分析显示，声学相似性是微调性能最强预测因子，而音素库与语言类型相似性更优解释零样本迁移效果。
原文摘要 · Abstract (English)
This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar languages outperform monolingual and multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological similarity better explain zero-shot transfer.
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。