Diff-ETS：学习用于肌电信号到语音转换的扩散概率模型
Diff-ETS: Learning a Diffusion Probabilistic Model for Electromyography-to-Speech Conversion
AI总结：
针对肌电转语音（ETS）合成语音自然度低的问题，提出基于分数扩散概率模型的Diff-ETS，通过优化EMG编码器预测的声学特征提升自然度，实验验证其效果显著优于基线模型。
摘要：
肌电信号到语音（Electromyography-to-Speech，ETS）转换通过在无声发音过程中从肌电（Electromyography，EMG）信号生成可听语音，已展现出在无声语音接口方面的潜力。ETS模型通常由将EMG信号转换为声学语音特征的EMG编码器，以及随后合成语音信号的声码器组成。由于可用数据量不足且信号存在噪声，合成的语音通常自然度较低。在本研究中，我们提出Diff-ETS，这是一种采用基于分数的扩散概率模型来提升合成语音自然度的ETS模型。该扩散模型用于改善由EMG编码器预测的声学特征的质量。在我们的实验中，我们评估了在预训练EMG编码器的预测结果上微调扩散模型，以及以端到端方式训练两个模型这两种方案。我们使用客观指标和听力测试将Diff-ETS与不含扩散模块的基线ETS模型进行了对比。结果表明，所提出的Diff-ETS相较于基线模型显著提升了语音自然度。
英文摘要：
Electromyography-to-Speech (ETS) conversion has demonstrated its potential for silent speech interfaces by generating audible speech from Electromyography (EMG) signals during silent articulations. ETS models usually consist of an EMG encoder which converts EMG signals to acoustic speech features, and a vocoder which then synthesises the speech signals. Due to an inadequate amount of available data and noisy signals, the synthesised speech often exhibits a low level of naturalness. In this work, we propose Diff-ETS, an ETS model which uses a score-based diffusion probabilistic model to enhance the naturalness of synthesised speech. The diffusion model is applied to improve the quality of the acoustic features predicted by an EMG encoder. In our experiments, we evaluated fine-tuning the diffusion model on predictions of a pre-trained EMG encoder, and training both models in an end-to-end fashion. We compared Diff-ETS with a baseline ETS model without diffusion using objective metrics and a listening test. The results indicated the proposed Diff-ETS significantly improved speech naturalness over the baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
