English

Neural2Speech: A Transfer Learning Framework for Neural-Driven Speech Reconstruction

Sound 2024-02-01 v2 Audio and Speech Processing Neurons and Cognition

Abstract

Reconstructing natural speech from neural activity is vital for enabling direct communication via brain-computer interfaces. Previous efforts have explored the conversion of neural recordings into speech using complex deep neural network (DNN) models trained on extensive neural recording data, which is resource-intensive under regular clinical constraints. However, achieving satisfactory performance in reconstructing speech from limited-scale neural recordings has been challenging, mainly due to the complexity of speech representations and the neural data constraints. To overcome these challenges, we propose a novel transfer learning framework for neural-driven speech reconstruction, called Neural2Speech, which consists of two distinct training phases. First, a speech autoencoder is pre-trained on readily available speech corpora to decode speech waveforms from the encoded speech representations. Second, a lightweight adaptor is trained on the small-scale neural recordings to align the neural activity and the speech representation for decoding. Remarkably, our proposed Neural2Speech demonstrates the feasibility of neural-driven speech reconstruction even with only 20 minutes of intracranial data, which significantly outperforms existing baseline methods in terms of speech fidelity and intelligibility.

Keywords

Cite

@article{arxiv.2310.04644,
  title  = {Neural2Speech: A Transfer Learning Framework for Neural-Driven Speech Reconstruction},
  author = {Jiawei Li and Chunxu Guo and Li Fu and Lu Fan and Edward F. Chang and Yuanning Li},
  journal= {arXiv preprint arXiv:2310.04644},
  year   = {2024}
}

Comments

To appear in 2024 IEEE International Conference on Acoustics, Speech and Signal Processing

R2 v1 2026-06-28T12:43:08.670Z