语言歧视提升多语言语音模型学习
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
苹果团队发现语言歧视能力能让多语音模型在相同数据预算下接近单语模型表现，对多语音AI开发很有启发。
苹果研究团队提出通过增强语言歧视能力提升多语言语音模型性能。在英语/法语HuBERT模型测试中，两种干预措施显著缩小了多语言模型与单语言模型之间的性能差距。该研究在连续语音和高级语言测量指标上均取得改进，同时保留了跨语言信息共享。
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing. Using a controlled English/French HuBERT setting, we test two interventions which strengthen language discrimination: an auxiliary language…
