Recurrent neural networks as neuro-computational models of human speech recognition.

Human speech recognition transforms a continuous acoustic signal into categorical linguistic units, by aggregating information that is distributed in time. It has been suggested that this kind of information processing may be understood through the computations of a Recurrent Neural Network (RNN) th...

Full description

Saved in:
Bibliographic Details
Main Authors: Christian Brodbeck, Thomas Hannagan, James S Magnuson
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-07-01
Series:PLoS Computational Biology
Online Access:https://doi.org/10.1371/journal.pcbi.1013244
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228221214621696
author Christian Brodbeck
Thomas Hannagan
James S Magnuson
author_facet Christian Brodbeck
Thomas Hannagan
James S Magnuson
author_sort Christian Brodbeck
collection DOAJ
description Human speech recognition transforms a continuous acoustic signal into categorical linguistic units, by aggregating information that is distributed in time. It has been suggested that this kind of information processing may be understood through the computations of a Recurrent Neural Network (RNN) that receives input frame by frame, linearly in time, but builds an incremental representation of this input through a continually evolving internal state. While RNNs can simulate several key behavioral observations about human speech and language processing, it is unknown whether RNNs also develop computational dynamics that resemble human neural speech processing. Here we show that the internal dynamics of long short-term memory (LSTM) RNNs, trained to recognize speech from auditory spectrograms, predict human neural population responses to the same stimuli, beyond predictions from auditory features. Variations in the RNN architecture motivated by cognitive principles further improved this predictive power. Specifically, modifications that allow more human-like phonetic competition also led to more human-like temporal dynamics. Overall, our results suggest that RNNs provide plausible computational models of the cortical processes supporting human speech recognition.
format Article
id doaj-art-54e6c0b6ab154aeba983a2b4e0af9f4a
institution Kabale University
issn 1553-734X
1553-7358
language English
publishDate 2025-07-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS Computational Biology
spelling doaj-art-54e6c0b6ab154aeba983a2b4e0af9f4a2025-08-23T05:31:13ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-07-01217e101324410.1371/journal.pcbi.1013244Recurrent neural networks as neuro-computational models of human speech recognition.Christian BrodbeckThomas HannaganJames S MagnusonHuman speech recognition transforms a continuous acoustic signal into categorical linguistic units, by aggregating information that is distributed in time. It has been suggested that this kind of information processing may be understood through the computations of a Recurrent Neural Network (RNN) that receives input frame by frame, linearly in time, but builds an incremental representation of this input through a continually evolving internal state. While RNNs can simulate several key behavioral observations about human speech and language processing, it is unknown whether RNNs also develop computational dynamics that resemble human neural speech processing. Here we show that the internal dynamics of long short-term memory (LSTM) RNNs, trained to recognize speech from auditory spectrograms, predict human neural population responses to the same stimuli, beyond predictions from auditory features. Variations in the RNN architecture motivated by cognitive principles further improved this predictive power. Specifically, modifications that allow more human-like phonetic competition also led to more human-like temporal dynamics. Overall, our results suggest that RNNs provide plausible computational models of the cortical processes supporting human speech recognition.https://doi.org/10.1371/journal.pcbi.1013244
spellingShingle Christian Brodbeck
Thomas Hannagan
James S Magnuson
Recurrent neural networks as neuro-computational models of human speech recognition.
PLoS Computational Biology
title Recurrent neural networks as neuro-computational models of human speech recognition.
title_full Recurrent neural networks as neuro-computational models of human speech recognition.
title_fullStr Recurrent neural networks as neuro-computational models of human speech recognition.
title_full_unstemmed Recurrent neural networks as neuro-computational models of human speech recognition.
title_short Recurrent neural networks as neuro-computational models of human speech recognition.
title_sort recurrent neural networks as neuro computational models of human speech recognition
url https://doi.org/10.1371/journal.pcbi.1013244
work_keys_str_mv AT christianbrodbeck recurrentneuralnetworksasneurocomputationalmodelsofhumanspeechrecognition
AT thomashannagan recurrentneuralnetworksasneurocomputationalmodelsofhumanspeechrecognition
AT jamessmagnuson recurrentneuralnetworksasneurocomputationalmodelsofhumanspeechrecognition