SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909460365049856 |
|---|---|
| author | Fan, Cunhang Zhang, Sheng Zhang, Jingjing Pan, Zexu Lv, Zhao |
| author_facet | Fan, Cunhang Zhang, Sheng Zhang, Jingjing Pan, Zexu Lv, Zhao |
| contents | Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain. Although breakthroughs have been made in reconstructing the mel spectrograms of audio stimuli perceived by subjects at the word or letter level using noninvasive electroencephalography (EEG), there is still a critical gap in precisely reconstructing continuous speech features, especially at the minute level. To address this issue, this paper proposes a State Space Model (SSM) to reconstruct the mel spectrogram of continuous speech from EEG, named SSM2Mel. This model introduces a novel Mamba module to effectively model the long sequence of EEG signals for imagined speech. In the SSM2Mel model, the S4-UNet structure is used to enhance the extraction of local features of EEG signals, and the Embedding Strength Modulator (ESM) module is used to incorporate subject-specific information. Experimental results show that our model achieves a Pearson correlation of 0.069 on the SparrKULee dataset, which is a 38% improvement over the previous baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG Fan, Cunhang Zhang, Sheng Zhang, Jingjing Pan, Zexu Lv, Zhao Signal Processing Sound Audio and Speech Processing Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain. Although breakthroughs have been made in reconstructing the mel spectrograms of audio stimuli perceived by subjects at the word or letter level using noninvasive electroencephalography (EEG), there is still a critical gap in precisely reconstructing continuous speech features, especially at the minute level. To address this issue, this paper proposes a State Space Model (SSM) to reconstruct the mel spectrogram of continuous speech from EEG, named SSM2Mel. This model introduces a novel Mamba module to effectively model the long sequence of EEG signals for imagined speech. In the SSM2Mel model, the S4-UNet structure is used to enhance the extraction of local features of EEG signals, and the Embedding Strength Modulator (ESM) module is used to incorporate subject-specific information. Experimental results show that our model achieves a Pearson correlation of 0.069 on the SparrKULee dataset, which is a 38% improvement over the previous baseline. |
| title | SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG |
| topic | Signal Processing Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.10402 |