Tokenizing Single-Channel EEG with Time-Frequency Motif Learning

TL;DR

The paper introduces TFM-Tokenizer, a novel EEG tokenization framework that learns time-frequency motifs to improve foundation model performance across diverse EEG tasks and devices.

Contribution

It proposes a dual-path architecture with time-frequency masking for robust motif learning, supporting various foundation models and operating at single-channel level.

Findings

Achieves up to 11% improvement in Cohen's Kappa on EEG benchmarks.

Boosts performance of foundation models like BIOT and LaBraM.

Outperforms baselines by 14% on ear-EEG sleep staging.

Abstract

Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from single-channel EEG signals and encodes them into discrete tokens. We propose a dual-path architecture with time-frequency masking to capture robust motif representations, and it is model-agnostic, supporting both lightweight transformers and existing foundation models for downstream tasks. Our study demonstrates three key benefits: Accuracy: Experiments on four diverse EEG benchmarks demonstrate consistent performance gains across both single- and multi-dataset pretraining settings, achieving up to $11\%$ improvement in Cohen's Kappa over strong baselines. Generalization: Moreover, as a plug-and-play component, it consistently boosts the performance of diverse foundation models, including BIOT and LaBraM. Scalability: By operating at the single-channel level rather than relying on the strict 10-20 EEG system, our method has the potential to be device-agnostic. Experiments on ear-EEG sleep staging, which differs from the pretraining data in signal format, channel configuration, recording device, and task, show that our tokenizer outperforms baselines by $14\%$. A comprehensive token analysis reveals strong class-discriminative, frequency-aware, and consistent structure, enabling improved representation quality and interpretability. Code is available at https://github.com/Jathurshan0330/TFM-Tokenizer.