Apple research says stronger language discrimination narrows the multilingual speech gap

Apple's machine learning research team reports that strengthening a model's ability to discriminate languages during pretraining narrows the gap between multilingual speech models and monolingual ones.

In a controlled English-French HuBERT setup, adding an auxiliary language classifier or per-language clustering targets cut phone discrimination error from 11.6% to 10.4%, below the monolingual model's 10.8%.

Lexical performance rose from 52.1% to 56.7%, still behind the monolingual 58.5%. These are the authors' own controlled experiments, and the findings are limited to the English-French setting.