论文标题
使用周期一致的对抗训练提高律师室外语音清晰度
Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training
论文作者
论文摘要
构造障碍是影响数百万人的电动演讲障碍。违反言语的差异远比非违反言论的人的理解力要差得多，从而造成了巨大的沟通困难。我们工作的目的是使用周期一致的GAN开发违反障碍的模型，以进行健康的语音转换。在先前的研究中，使用18,700次肌音和8,610个健康控制韩国话语，目的是自动识别语音键盘，对发电机进行了训练，可以将质心转化为光谱域中的健康语音，然后将其转化为语音。使用对持有的测试集中生成的话语的自动语音识别的客观评估表明，与原始辞职障碍语音进行对抗训练后，识别性能得到了改善，因为绝对WER降低了33.4％。它表明，拟议的基于GAN的转换方法对于提高质心语音清晰度很有用。
Dysarthria is a motor speech impairment affecting millions of people. Dysarthric speech can be far less intelligible than those of non-dysarthric speakers, causing significant communication difficulties. The goal of our work is to develop a model for dysarthric to healthy speech conversion using Cycle-consistent GAN. Using 18,700 dysarthric and 8,610 healthy control Korean utterances that were recorded for the purpose of automatic recognition of voice keyboard in a previous study, the generator is trained to transform dysarthric to healthy speech in the spectral domain, which is then converted back to speech. Objective evaluation using automatic speech recognition of the generated utterance on a held-out test set shows that the recognition performance is improved compared with the original dysarthic speech after performing adversarial training, as the absolute WER has been lowered by 33.4%. It demonstrates that the proposed GAN-based conversion method is useful for improving dysarthric speech intelligibility.
