Synapse Open Synapse
Biology

Interpretable Embeddings of Speech Enhance and Explain Brain Encoding Performance of Audio Models

arXiv q-bio · · 1 min read

arXiv:2507.16080v3 Announce Type: replace Abstract: Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception. However, since their representations are inherently black-box, it remains unclear what drives their alignment with brain responses.

Latest from arXiv q-bio