AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Do speech foundation models really learn words?

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-aware language models. Attempts to understand their usefulness have largely focused on probing their representations' ability to discriminate phonemes and words. However, discriminative ability for words need not imply specialized representation of words per se. Good discrimination of words may be explained by good encoding of word form (phonemes) rather than form-independent word representations encoding identity or sy

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T19:32:24.350Z. This is not the publication date.