Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings

TL;DR

This paper introduces H2DiLR, a novel framework that disentangles neural homogeneity and heterogeneity to improve lexical tone decoding from intracranial recordings across multiple subjects, advancing brain-computer interface capabilities for speech-impaired tonal language speakers.

Contribution

The paper presents H2DiLR, a new method that effectively captures shared and individual neural features for improved cross-subject lexical tone decoding.

Findings

H2DiLR significantly outperforms traditional heterogeneous decoding methods.

H2DiLR effectively captures both homogeneity and heterogeneity in neural representations.

The framework demonstrates robust decoding across multiple Mandarin syllables.

Abstract

Recent advancements in brain-computer interfaces (BCIs) have enabled the decoding of lexical tones from intracranial recordings, offering the potential to restore the communication abilities of speech-impaired tonal language speakers. However, data heterogeneity induced by both physiological and instrumental factors poses a significant challenge for unified invasive brain tone decoding. Traditional subject-specific models, which operate under a heterogeneous decoding paradigm, fail to capture generalized neural representations and cannot effectively leverage data across subjects. To address these limitations, we introduce Homogeneity-Heterogeneity Disentangled Learning for neural Representations (H2DiLR), a novel framework that disentangles and learns both the homogeneity and heterogeneity from intracranial recordings across multiple subjects. To evaluate H2DiLR, we collected stereoelectroencephalography (sEEG) data from multiple participants reading Mandarin materials comprising 407 syllables, representing nearly all Mandarin characters. Extensive experiments demonstrate that H2DiLR, as a unified decoding paradigm, significantly outperforms the conventional heterogeneous decoding approach. Furthermore, we empirically confirm that H2DiLR effectively captures both homogeneity and heterogeneity during neural representation learning.