Papers

BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0

International Conference
2021~
작성자
dsp
작성일
2023-08-11 11:32
조회
574
Authors : Miseul Kim, Zhenyu Piao, Jihyun Lee, Hong-Goo Kang

Year : 2023

Publisher / Conference : The IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)

Research area : Speech Signal Processing, Etc


Presentation : Poster

Decoding spoken speech from neural activity in the brain is a fast-emerging research topic, as it could enable communication for people who have difficulties with producing audible speech. For this task, electrocorticography (ECoG) is a common method for recording brain activity with high temporal resolution and high spatial precision. However, due to the risky surgical procedure required for obtaining ECoG recordings, relatively little of this data has been collected, and the amount is insufficient to train a neural network-based Brain-to-Speech (BTS) system. To address this problem, we propose BrainTalker—a novel BTS framework that generates intelligible spoken speech from ECoG signals under extremely low-resource scenarios. We apply a transfer learning approach utilizing a pre-trained self-supervised model, Wav2Vec 2.0. Specifically, we train an encoder module to map ECoG signals to latent embeddings that match Wav2Vec 2.0 representations of the corresponding spoken speech. These embeddings are then transformed into mel-spectrograms using stacked convolutional and transformer-based layers, which are fed into a neural vocoder to synthesize speech waveform. Experimental results demonstrate our proposed framework achieves outstanding performance in terms of subjective and objective metrics, including a Pearson correlation coefficient of 0.9 between generated and ground truth mel-spectrograms. We share publicly available Demos and Code.
전체 355
142 International Conference Seyun Um, Jihyun Kim, Jihyun Lee, Hong-Goo Kang "Facetron: A Multi-speaker Face-to-Speech Model based on Cross-Modal Latent Representations" in EUSIPCO, 2023
141 International Conference Hejung Yang, Hong-Goo Kang "Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement" in INTERSPEECH, 2023
140 International Conference Jihyun Kim, Hong-Goo Kang "Contrastive Learning based Deep Latent Masking for Music Source Seperation" in INTERSPEECH, 2023
139 International Conference Woo-Jin Chung, Doyeon Kim, Soo-Whan Chung, Hong-Goo Kang "MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion" in INTERSPEECH, 2023
138 International Conference Hyungchan Yoon, Seyun Um, Changhwan Kim, Hong-Goo Kang "Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech" in INTERSPEECH, 2023
137 International Conference Hyungchan Yoon, Changhwan Kim, Eunwoo Song, Hyun-Wook Yoon, Hong-Goo Kang "Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech" in INTERSPEECH, 2023
136 International Conference Doyeon Kim, Soo-Whan Chung, Hyewon Han, Youna Ji, Hong-Goo Kang "HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders" in INTERSPEECH, 2023
135 International Conference Zhenyu Piao, Miseul Kim, Hyungchan Yoon, Hong-Goo Kang "HappyQuokka System for ICASSP 2023 Auditory EEG Challenge" in ICASSP, 2023
134 International Conference Byeong Hyeon Kim, Hyungseob Lim, Jihyun Lee, Inseon Jang, Hong-Goo Kang "Progressive Multi-Stage Neural Audio Codec with Psychoacoustic Loss and Discriminator" in ICASSP, 2023
133 International Conference Hyungseob Lim, Jihyun Lee, Byeong Hyeon Kim, Inseon Jang, Hong-Goo Kang "End-to-End Neural Audio Coding in the MDCT Domain" in ICASSP, 2023