FOCUSING ON ATTENTION: PROSODY TRANSFER AND ADAPTATIVE OPTIMIZATION STRATEGY FOR MULTI-SPEAKER END-TO-END SPEECH SYNTHESIS | |
Fu, Ruibo1,2; Tao, Jianhua1,2,3; Wen, Zhengqi2; Yi, Jiangyan2; Wang, Tao1,2 | |
2020-05 | |
会议日期 | 2020-5 |
会议地点 | 网上虚拟会议 |
关键词 | prosody transfer optimization strategy speaker adaptation attention speech synthesis |
英文摘要 | End-to-end speech synthesis can generate high-quality synthetic speech and achieve high similarity scores with low-resource adaptation data. However, the generalization of out-domain texts is still a challenging task. The limited adaptation data leads to unacceptable errors and the poor prosody performance of the synthetic speech. In this paper, we present two novel methods to handle the above problems by focusing on the attention. Firstly, compared with the conventional methods that extract prosody embeddings for conditioning input, a duration controller with feedback mechanism is proposed, which can control the states transition in the sequence-to-sequence model more directly and precisely. Secondly, to alleviate the unmatching text-audio pairs’ impact on model, an adaptative optimization strategy which would consider the matching degree of the training sample is also proposed. Experimental results on Mandarin dataset show that proposed methods lead to an improvement on both robustness and overall naturalness. |
源文献作者 | IEEE |
会议录出版者 | ieee |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39596] |
专题 | 模式识别国家重点实验室_智能交互 |
通讯作者 | Fu, Ruibo |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
推荐引用方式 GB/T 7714 | Fu, Ruibo,Tao, Jianhua,Wen, Zhengqi,et al. FOCUSING ON ATTENTION: PROSODY TRANSFER AND ADAPTATIVE OPTIMIZATION STRATEGY FOR MULTI-SPEAKER END-TO-END SPEECH SYNTHESIS[C]. 见:. 网上虚拟会议. 2020-5. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论