# Joint Text-Audio Alignment for EEG-to-Text Decoding in Chinese Speech Production and Perception

arXiv: https://arxiv.org/abs/2607.25626 · HTML: https://mlsanity.com/paper/2607.25626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Decoding speech perception from non-invasive brain recordings](https://mlsanity.com/paper/2208.12266/) (2022)
- [NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals](https://mlsanity.com/paper/2409.00101/) (2024)
- [Transfer Learning in Brain-Computer Interfaces](https://mlsanity.com/paper/1512.00296/) (2015)
- [EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer](https://mlsanity.com/paper/2405.02165/) (2024)
- [Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder](https://mlsanity.com/paper/2402.17433/) (2024)
- [Scaling Law in Neural Data: Non-Invasive Speech Decoding with 175 Hours of EEG Data](https://mlsanity.com/paper/2407.07595/) (2024)
- [ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG](https://mlsanity.com/paper/2401.04965/) (2024)
- [SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG](https://mlsanity.com/paper/2501.10402/) (2025)
- [EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEG](https://mlsanity.com/paper/2506.00854/) (2025)
- [Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording](https://mlsanity.com/paper/2401.04964/) (2024)
- [DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction](https://mlsanity.com/paper/2507.07526/) (2025)

## Abstract (arXiv)

Decoding speech information directly from scalp electroencephalography (EEG) into text provides a potential non-invasive neural communication pathway for individuals with severe speech and motor impairments. Compared with invasive approaches such as electrocorticography, EEG is safer and more widely deployable, yet substantially more challenging to decode.This challenge is exacerbated for Chinese sentence decoding, which must handle a high-dimensional output space with thousands of characters, severe inter-subject variability, and low signal-to-noise ratios for text alignment.Existing methods commit to a single supervisory axis---either text semantics or audio acoustic features---yet neither can simultaneously satisfy the demands of sentence-level discriminability and fine-grained temporal resolution required for large-vocabulary Chinese decoding. We introduce EEGAlign, a novel parameter-efficient framework that jointly aligns EEG with two axes---text alignment with BGE-M3 text embeddings and audio alignment with wav2vec~2.0 speech features via contrastive learning followed by CTC character-sequence decoding. On ChineseEEG-2 data, EEGAlign yields state-of-the-art closed-set sentence classification performance, reaching up to 82.37% Top-1 accuracy on Reading Aloud EEG and 41.43% on Passive Listening EEG out of 101 candidates. Ablation studies show that the two alignment axes are highly complementary: combining them yields consistently better performance than either alone. To the best of our knowledge, this is the first study on decoding large-vocabulary Chinese sentences from non-invasive EEG during overt speech production, and achieving strong classification performance with relatively large closed-set candidate-sentence setting.