arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03786eess.AScs.LGcs.SDeess.SP
收藏

EMA2S:一个端到端的多模态发音转语音系统

EMA2S: An End-to-End Multimodal Articulatory-to-Speech System

Research Center for Information Technology Innovation, Academia Sinica(中央研究院资讯科技创新研究中心);Institute of Information Science, Academia Sinica(中央研究院资讯科学研究所);Graduate School of Informatics, Nagoya University(名古屋大学信息学研究科);National Institute of Information and Communications Technology(国立信息通信技术研究所)

Yu-Wen Chen, Kuo-Hsuan Hung, Shang-Yi Chuang, Jonathan Sherman, Wen-Chin Huang, Xugang Lu, Yu Tsao

摘要:

从发音运动合成的语音可以在现实世界中用于声带疾病患者,需要无声语音的情况下,或在高噪音环境中。在这项工作中,我们提出了EMA2S,一个端到端的多模态发音到语音系统,直接将发音运动的语音信号。我们使用基于神经网络的声码器结合多模态联合训练,将频谱图,梅尔频谱图和深度特征。实验结果证实,多模态方法的EMA2S优于基线系统的客观评价和主观评价指标。此外,实验结果表明,联合梅尔谱图和深度特征丢失训练可以有效地提高系统的性能。

英文摘要:

Synthesized speech from articulatory movements can have real-world use for patients with vocal cord disorders, situations requiring silent speech, or in high-noise environments. In this work, we present EMA2S, an end-to-end multimodal articulatory-to-speech system that directly converts articulatory movements to speech signals. We use a neural-network-based vocoder combined with multimodal joint-training, incorporating spectrogram, mel-spectrogram, and deep features. The experimental results confirm that the multimodal approach of EMA2S outperforms the baseline system in terms of both objective evaluation and subjective evaluation metrics. Moreover, results demonstrate that joint mel-spectrogram and deep feature loss training can effectively improve system performance.

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。

↑