Boundary conditions for cortical speech tracking as an objective speech-in-noise marker: a three-dataset MEG/EEG benchmark

electrophysiological markers are often proposed for speech-in-noise assessment, but their validation targets are not always explicit: a marker may calibrate with intelligibility, distinguish acoustic conditions, decode attention, or predict an individual speech reception threshold (SRT). We used three public MEG/EEG datasets to test these endpoints within one validation framework....

Continue reading at PubMed →

Cortical speech tracking shows promise as an objective speech-in-noise marker, but boundary conditions identified across three datasets mean it is not yet ready for routine clinical use; researchers should note the benchmark parameters before designing new studies.

A validated objective measure of speech-in-noise ability would transform audiological assessment, especially for populations who cannot complete traditional behavioral tests, making this benchmark work a key methodological stepping stone.

1. 01Benchmarks cortical speech tracking (brain-following-speech signal) as an objective speech-in-noise test across three independent datasets.
2. 02Uses both MEG (magnetic brain imaging) and EEG (electrical brain imaging) to assess generalizability of the marker.
3. 03Identifies specific boundary conditions—signal parameters that must be met for the measure to work reliably.
4. 04Objective speech-in-noise markers could one day benefit patients unable to complete behavioral audiometry.
5. 05Published in Hearing Research, a leading peer-reviewed auditory science journal.

PMID

42805137

DOI

10.1016/j.heares.2026.109816.

Journal

Hearing Research

Publication type

research_article

Evidence level

2b

Population

Participants assessed for speech-in-noise perception across three MEG/EEG datasets

Intervention

Cortical speech tracking measured via MEG and EEG

Comparator

Behavioral speech-in-noise assessment