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, o…
Read the full story at Apple Machine Learning Research ↗
Timeline · 1 report
- 2026-10-02 00:00 · Apple Machine Learning Research
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models