Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
TL;DR · AI 摘要
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models - Apple Machine Learning Research res...
核心要点
- 主题聚焦：Language Discrimination Improves Linguistic Lear
- 来源：Apple Machine Learning Research，建议结合原文判断细节。
- AI 分析暂不可用，本条为保底评分与摘要。
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models - Apple Machine Learning Research
research area
Speech and Natural Language Processing
content type
paper
published
October 2026
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Authors Maureen de Seyssel, Jie Chi*, Zakaria Aldeneh*
View publication
Copy Bibtex
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 modelâs 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,â) decreases from 11.6% in the bilingual baseline to 10.4% (monolingual: 10.8%), while lexical performance (sWUGGY,â) increases from 52.1% to 56.7% (monolingual: 58.5%) and prosodic performance (ProsAudit, lexical subtask,â) 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.
- * Equal contribution
Related readings and updates.
Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models
September 25, 2025 research area Speech and Natural Language Processing conference ICASSP
Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual settings. However, multilingual SSL models tend to underperform their monolingual counterparts on each individual language, especially in multilingual scenarios with few languages such as the bilingual setting. Inâ¦
Read more
Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks
June 13, 2025 research area Speech and Natural Language Processing conference EMNLP
We introduce a set of training-free ABX-style discrimination tasks to evaluate how multilingual language models represent language identity (form) and semantic content (meaning). Inspired from speech processing, these zero-shot tasks measure whether minimal differences in representation can be reliably detected. This offers a flexible and interpretable alternative to probing. Applied to XLM-R (Conneau et al, 2020) across pretraining checkpointsâ¦
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.
Work with us