.png){kind=icon}
返回
Statistical Parametric Speech Synthesis Using Deep Gaussian Processes
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2019.2905167.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper proposes a framework of speech synthesis based on deep Gaussian processes (DGPs), which is a deep architecture model composed of stacked Bayesian kernel regressions. In this method, we train a statistical model of transformation from contextual features to speech parameters in a similar manner to deep neural network (DNN)-based speech synthesis. To apply DGPs to a statistical parametric speech synthesis framework, our framework uses an approximation method, doubly stochastic variational inference, which is suitable for an arbitrary amount of data. Since the training of DGPs is based on the marginal likelihood that takes into account not only data fitting, but also model complexity, DGPs are less vulnerable to overfitting compared with DNNs. In experimental evaluations, we investigated a performance comparison of the proposed DGP-based framework with a feedforward DNN-based one. Subjective and objective evaluation results showed that our DGP framework yielded a higher mean opinion score and lower acoustic feature distortions than the conventional framework.
Keyword:
Statistical parametric speech synthesis
Gaussian process
stochastic variational inference
Bayesian model
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Genome Sequence of Ralstonia pseudosolanacearum Strains with Compatible and Incompatible Interactions with the Major Tomato Resistance Source Hawaii 7996与主要番茄抗性来源Hawaii 7996具有亲和性和非亲和性互作关系的Ralstonia pseudosolanacearum菌株的基因组序列OAAI
.png){kind=icon}
OAAI分享收藏
Glass fiber/epoxy composites with integrated layer of carbon nanotubes for deformation detection
PREAI
分享收藏分享收藏
查看更多内容