CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis
Wen ZQ(温正棋)1; Li Y(李雅)1; Tao JH(陶建华)1,2; Wen, Zhengqi
2016-09
会议名称Annual Conference of the International Speech Communication Association-Interspeech
会议录名称INTERSPEECH
会议日期Sep 8-12, 2016
会议地点San Francisco,USA
摘要In the speech synthesis systems, the phoneme identity feature indicated as the pronunciation unit is influenced by external contexts like the neighboring words and phonemes. This paper proposes to encode such relatedness and parameterize the pronunciation of the phoneme identity feature as a continuous real-valued vector. The vector, composed by a phoneme embedded vector (PEV) and a word embedded vector (WEV), is applied to substitute the binary vector whose representation is one-hot. It is realized in the word embedding model with the joint training structure where the PEV and WEV are learned together. The effectiveness of the proposed technique was evaluated by comparing it with the binary vector in the bidirectional long short term memory recurrent neural network (BLSTM-RNN) based speech synthesis systems. Improvement on the quality of the synthesized speech has been achieved from the proposed system, which proves the effectiveness of replacing the binary vector with the continuous real-valued vector in describing the phoneme identity feature.
关键词Phoneme Embedded Vector Word Embedding Speech Synthesis Blstm-rnn
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12476
专题模式识别国家重点实验室_语音交互
通讯作者Wen, Zhengqi
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
推荐引用方式
GB/T 7714
Wen ZQ,Li Y,Tao JH,et al. The Parameterized Phoneme Identity Feature as a Continuous Real-Valued Vector for Neural Network based Speech Synthesis[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2016.06.21_final.pdf(541KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wen ZQ(温正棋)]的文章
[Li Y(李雅)]的文章
[Tao JH(陶建华)]的文章
百度学术
百度学术中相似的文章
[Wen ZQ(温正棋)]的文章
[Li Y(李雅)]的文章
[Tao JH(陶建华)]的文章
必应学术
必应学术中相似的文章
[Wen ZQ(温正棋)]的文章
[Li Y(李雅)]的文章
[Tao JH(陶建华)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2016.06.21_final.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。