Using Speech Enhancement to Realize Speech Synthesis of Low-Resource Dungan Languages
2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)(2021)
摘要
Deep learning-based speech synthesis has shown great potential in the quality of synthetic speech. However, as deep learning approaches need an abundant amount of training data, lacking training data will affect the quality of synthesized speech for low-resource Dungan languages since it is challenging to obtain high-quality training data. This paper realized a Dungan speech synthesis that uses a ...
更多查看译文
关键词
Training,Learning systems,Vocoders,Transfer learning,Training data,Speech enhancement,Transformers
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要