云南省人工智能重点实验室

科研成果

当前位置：首页>科研成果>论文列表

论文作者：	Linqin Wang;Zhengtao Yu*;Yuanzhang Yang;Shengxiang Gao;Cubli Mao;Yuxin Huang
论文名称：	Non-parallel Accent Transfer based on Fine-grained Controllable Accent Modeling
论文发表刊物：	The 2023 Conference on Empirical Methods in Natural Language Processing
会议地点：
会议时间：
卷号页码：
论文描述：
收录情况：	EI Indexed
论文摘要：
Existing accent transfer works rely on parallel data or speech recognition models. This paper focuses on the practical application of accent transfer and aims to implement accent transfer using non-parallel datasets. The study has encountered the challenge of speech representation disentanglement and modeling accents. In our accent modeling transfer framework, we manage to solve these problems by two proposed methods. First, we learn the suprasegmental information associated with tone to finely model the accents in terms of tone and rhythm. Second, we propose to use mutual information learning to disentangle the accent features and control the accent of the generated speech during the inference time. Experiments show that the proposed framework attains superior performance to the baseline models in terms of accentedness and audio quality.
点击此处下载文章内容