Predicting Natural Speech EEG Recordings with a Contextualized Speech Model.

<p>EEG recordings of audiobook comprehension were analyzed. The audiobook waveform was processed through a pre-trained deep-learning speech model (Whisper-base). A sliding window approach was applied to feed the model up to 30s of prior speech audio waveform, which was then re-represented as a...

Full description

Saved in:

Bibliographic Details
Main Author:	Andrew J. Anderson (20161392) (author)
Other Authors:	Chris Davis (647632) (author), Edmund C. Lalor (11450457) (author)
Published:	2024
Subjects:	Neuroscience Physiology Sociology Science Policy Biological Sciences not elsewhere classified speaker &# 8220 layer depth advantage intermediary representational stage learning models reveal transform continuous speech selectively attended speech contained eeg model complete brain models accurate eeg models model eeg recordings models may complete picture eeg modeling brain responses brain mechanism model electroencephalogram unattended speech speech rate xlink "> whisper provides text transformation superficial level reflects elements providing end promising approach listening conditions linguistic processing lexical representation end accounts audiobook comprehension
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Predicting Natural Speech EEG Recordings with a Contextualized Speech Model.

Similar Items