Towards an analytical framework for investigating the neurophysiological influence of social context in speech perception
- 1Trinity College Dublin
Abstract
Social information plays an important role in everyday speech communication, yet existing neurophysiological approaches provide limited means of isolating its contribution during naturalistic speech perception. Here, we present an analytical framework that combines the large language model (LLM) Mistral-Instruct, fine-tuned on conversational language, and temporal response functions (TRFs) to investigate the influence of social context on word-level speech processing. The framework disentangles local context (LC) from speaker-specific social context (SC) when generating LLM-derived lexical expectation measures, enabling such predictions to be generated under either matching or mismatching speaker contexts for the same speech material. This provides a direct way of isolating the contribution of social information to lexical predictions. We first show that speaker-related social context carries information about speech register and conversational role beyond that available from previous local context alone by interrogating Mistral-Instruct. We then demonstrate that lexical expectations generated from socially congruent contexts produce small but reliable improvements in EEG prediction relative to expectations generated from incongruent social contexts. These effects were observed despite identical acoustic input and neural recordings, indicating that the influence of social context on lexical expectations explains dissociable variance in neural responses to speech. Together, these findings provide a proof of concept for using LLM-derived lexical expectations to isolate and measure the influence of social context on speech processing. More broadly, the proposed framework offers a flexible approach for generating and testing hypotheses about how different forms of contextual knowledge shape neural responses during naturalistic language comprehension.
Related
- Beyond snapshots: A dynamic framework for continuous motor unit tracking to enhance neurophysiological assessments
- Predictive biases in emotional perception: differential influence of mood and affective primes in individuals with and without mood disorders
- Influence of the anaesthetist´s perception on the evaluation of recovery quality in horses undergoing general anaesthesia
- Subject-independent classification of ADHD from pediatric EEG: a leakage-aware deep learning framework with interpretable neurophysiological mapping
- Contextual modulations at low and high levels of visual perception: functional (in)dependence and influence of local contrast
BibTeX
@misc{ip2026towards,
title = {{Towards an analytical framework for investigating the neurophysiological influence of social context in speech perception}},
author = {E. Y. J. Ip and A. Igoe and B. R. Cowan and G. M. Di Liberto},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.05.764590},
url = {https://www.biorxiv.org/content/10.64898/2026.11.05.764590v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Towards an analytical framework for investigating the neurophysiological influence of social context in speech perception
AU - E. Y. J. Ip
AU - A. Igoe
AU - B. R. Cowan
AU - G. M. Di Liberto
PY - 2026
DA - 2026/11/05
PB - bioRxiv
DO - 10.64898/2026.11.05.764590
UR - https://www.biorxiv.org/content/10.64898/2026.11.05.764590v1
AB - Social information plays an important role in everyday speech communication, yet existing neurophysiological approaches provide limited means of isolating its contribution during naturalistic speech perception. Here, we present an analytical framework that combines the large language model (LLM) Mistral-Instruct, fine-tuned on conversational language, and temporal response functions (TRFs) to investigate the influence of social context on word-level speech processing. The framework disentangles local context (LC) from speaker-specific social context (SC) when generating LLM-derived lexical expectation measures, enabling such predictions to be generated under either matching or mismatching speaker contexts for the same speech material. This provides a direct way of isolating the contribution of social information to lexical predictions. We first show that speaker-related social context carries information about speech register and conversational role beyond that available from previous local context alone by interrogating Mistral-Instruct. We then demonstrate that lexical expectations generated from socially congruent contexts produce small but reliable improvements in EEG prediction relative to expectations generated from incongruent social contexts. These effects were observed despite identical acoustic input and neural recordings, indicating that the influence of social context on lexical expectations explains dissociable variance in neural responses to speech. Together, these findings provide a proof of concept for using LLM-derived lexical expectations to isolate and measure the influence of social context on speech processing. More broadly, the proposed framework offers a flexible approach for generating and testing hypotheses about how different forms of contextual knowledge shape neural responses during naturalistic language comprehension.
ER -