Parallel hierarchical encoding of linguistic representations in the human auditory cortex and recurrent automatic speech recognition systems
Menoua Keshishian, Gavin Mischler, Samuel Thomas, Brian E. D. Kingsbury, Stephan Bickel, Ashesh D. Mehta, Nima Mesgarani
This study compares the hierarchical processing of speech in the human auditory cortex with a recurrent ASR model, finding parallel representations across acoustic, phonetic, lexical, and semantic stages.
Nature Machine Intelligence · Feb 17, 2026Peer-reviewedNeuroscience