First Step Towards End-to-end Parametric TTS Synthesis: Generating Spectral Parameters with Neural Attention

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	First Step Towards End-to-end Parametric TTS Synthesis: Generating Spectral Parameters with Neural Attention
	Wang, Wenfu; Xu, Shuang; Xu, Bo
	2016-09
会议日期	2016-9-8
会议地点	San Francisco, USA
关键词	Parametric Tts Synthesis End-to-end Attention Based Recurrent Neural Network Acoustic Modeling
页码	2243-2247
英文摘要	In conventional neural networks (NN) based parametric text-to-speech (TTS) synthesis frameworks, text analysis and acoustic modeling are typically processed separately, leading to some limitations. On one hand, much significant human expertise is normally required in text analysis, which presents a laborious task for researchers; on the other hand, training of the NN-based acoustic models still relies on the hidden Markov model (HMM) to obtain frame-level alignments. This acquisition process normally goes through multiple complicated stages. The complex pipeline makes constructing a NN-based parametric TTS system a challenging task. This paper attempts to bypass these limitations using a novel end-to-end parametric TTS synthesis framework, i.e. the text analysis and acoustic modeling are integrated together employing an attention-based recurrent neural network. Thus the alignments can be learned automatically. Preliminary experimental results show that the proposed system can generate moderately smooth spectral parameters and synthesize fairly intelligible speech on short utterances (less than 8 Chinese characters).
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/19657]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
作者单位	Institute of Automation, Chinese Academy of Sciences, China
推荐引用方式 GB/T 7714	Wang, Wenfu,Xu, Shuang,Xu, Bo. First Step Towards End-to-end Parametric TTS Synthesis: Generating Spectral Parameters with Neural Attention[C]. 见:. San Francisco, USA. 2016-9-8.