@inproceedings{zhang-etal-2026-temporal,
title = "Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals",
author = "Zhang, Zhejun and
Zhou, Wenqing and
Xu, Haozhe and
Zhang, Lin and
Li, Lei",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1911/",
pages = "41208--41226",
ISBN = "979-8-89176-390-6",
abstract = "Brain-tuning enhances brain alignment and downstream performance by fine-tuning speech language models with neural recordings. However, previous work relies primarily on fMRI, whose temporal resolution integrates neural activity over seconds, blending distinct processing stages into a single supervision signal and precluding temporally targeted training. We introduce ECoG-tuning, which leverages electrocorticography{'}s millisecond precision to train speech language models. We design temporally targeted windows{---}a speech window capturing acoustic-phonetic encoding and a language window capturing higher-order linguistic processing{---}grounded in neuroscientific findings about temporal encoding hierarchies. Evaluating three models on the Podcast ECoG dataset, we find that ECoG-tuning significantly improves brain alignment over pretrained and distillation baselines. Notably, full spatiotemporal dynamics yield 7{--}17{\%} higher alignment than time-averaged supervision across models, and language-window tuning produces larger gains in higher-order language regions, indicating that temporal precision provides additional training value. Moreover, ECoG-tuned models consistently improve or maintain downstream performance. Overall, our work provides initial evidence that electrophysiology is a viable brain-tuning modality, demonstrating how neuroscientific insights into processing hierarchies can inform principled model training strategies. Code is available at [https://github.com/Mochizuki-BUPT/ECoG-Tuning-main](https://github.com/Mochizuki-BUPT/ECoG-Tuning-main)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-temporal">
<titleInfo>
<title>Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhejun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqing</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haozhe</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Brain-tuning enhances brain alignment and downstream performance by fine-tuning speech language models with neural recordings. However, previous work relies primarily on fMRI, whose temporal resolution integrates neural activity over seconds, blending distinct processing stages into a single supervision signal and precluding temporally targeted training. We introduce ECoG-tuning, which leverages electrocorticography’s millisecond precision to train speech language models. We design temporally targeted windows—a speech window capturing acoustic-phonetic encoding and a language window capturing higher-order linguistic processing—grounded in neuroscientific findings about temporal encoding hierarchies. Evaluating three models on the Podcast ECoG dataset, we find that ECoG-tuning significantly improves brain alignment over pretrained and distillation baselines. Notably, full spatiotemporal dynamics yield 7–17% higher alignment than time-averaged supervision across models, and language-window tuning produces larger gains in higher-order language regions, indicating that temporal precision provides additional training value. Moreover, ECoG-tuned models consistently improve or maintain downstream performance. Overall, our work provides initial evidence that electrophysiology is a viable brain-tuning modality, demonstrating how neuroscientific insights into processing hierarchies can inform principled model training strategies. Code is available at [https://github.com/Mochizuki-BUPT/ECoG-Tuning-main](https://github.com/Mochizuki-BUPT/ECoG-Tuning-main).</abstract>
<identifier type="citekey">zhang-etal-2026-temporal</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1911/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>41208</start>
<end>41226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals
%A Zhang, Zhejun
%A Zhou, Wenqing
%A Xu, Haozhe
%A Zhang, Lin
%A Li, Lei
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F zhang-etal-2026-temporal
%X Brain-tuning enhances brain alignment and downstream performance by fine-tuning speech language models with neural recordings. However, previous work relies primarily on fMRI, whose temporal resolution integrates neural activity over seconds, blending distinct processing stages into a single supervision signal and precluding temporally targeted training. We introduce ECoG-tuning, which leverages electrocorticography’s millisecond precision to train speech language models. We design temporally targeted windows—a speech window capturing acoustic-phonetic encoding and a language window capturing higher-order linguistic processing—grounded in neuroscientific findings about temporal encoding hierarchies. Evaluating three models on the Podcast ECoG dataset, we find that ECoG-tuning significantly improves brain alignment over pretrained and distillation baselines. Notably, full spatiotemporal dynamics yield 7–17% higher alignment than time-averaged supervision across models, and language-window tuning produces larger gains in higher-order language regions, indicating that temporal precision provides additional training value. Moreover, ECoG-tuned models consistently improve or maintain downstream performance. Overall, our work provides initial evidence that electrophysiology is a viable brain-tuning modality, demonstrating how neuroscientific insights into processing hierarchies can inform principled model training strategies. Code is available at [https://github.com/Mochizuki-BUPT/ECoG-Tuning-main](https://github.com/Mochizuki-BUPT/ECoG-Tuning-main).
%U https://aclanthology.org/2026.acl-long.1911/
%P 41208-41226
Markdown (Informal)
[Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals](https://aclanthology.org/2026.acl-long.1911/) (Zhang et al., ACL 2026)
ACL