Knowledge Commons of Institute of Automation,CAS
Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer | |
Fu, Ruibo1,2; Tao, Jianhua1,2,3; Zheng, Yibin1,2; Wen, Zhengqi1 | |
2018-09 | |
会议名称 | INTERPSEECH2018 |
会议日期 | 2018-9 |
会议地点 | 印度海得拉巴 |
摘要 | This paper describes a unified Deep Metric Learning (DML) framework to predict the target cost directly by supervised learning method. The conventional methods to calculate the target cost include two separate steps: feature extraction and standard distance measurement. The proposed DML framework aims to measure the similarity between the candidate units and the target units more reasonably and directly. Firstly, the symmetrical DML framework is pre-trained to learn the metric between pairs of candidate units and the target units. The relabeling procedure is added to correct the initial designed label of the target cost. Secondly, the acoustic features of the target units is removed, which fits the runtime of the unit-selection synthesizer. The asymmetrical DML is fine-tuned to learn the metric between candidate units and target units. Compared to the conventional methods, the proposed unified DML framework can avoid the accumulation of errors in separate steps and improve the accuracy in labeling and predicting the target cost. The evaluation results demonstrate that the naturalness of synthetic speech has been improved by adopting DML framework to predict target cost. |
关键词 | speech synthesis unit-selection target cost deep metric learning |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39597 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
通讯作者 | Fu, Ruibo |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.CAS Center for Excellence in Brain Science and Intelligence Technology 3.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Fu, Ruibo,Tao, Jianhua,Zheng, Yibin,et al. Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
INTERSPEECH2018_1305(323KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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