Language Discrimination Improves Linguistic Learning in Multilingual Speech Models

Language Discrimination Improves Linguistic Learning in Multilingual Speech Models

AuthorsMaureen de Seyssel, Jie Chi*, Zakaria Aldeneh*

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 classifier and per-language k-means targets. Across interventions, continuous-feature phone discrimination error (phone-ABX,↓) decreases from 11.6% in the bilingual baseline to 10.4% (monolingual: 10.8%), while lexical performance (sWUGGY,↑) increases from 52.1% to 56.7% (monolingual: 58.5%) and prosodic performance (ProsAudit, lexical subtask,↑) from 68.9% to 72.9% (monolingual: 72.6%). Across HuBERT training stages, the strongest gains on most linguistic measures occur when language discrimination is introduced in the first iteration, whereas later or repeated interventions yield smaller improvements and are accompanied by increased language-wise segregation. These results support a causal role for language discrimination in reducing the additional cost of multilingual learning.

Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models