.png){kind=icon}
返回
SFNet: A Computationally Efficient Source Filter Model Based Neural Speech Synthesis
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2020.3005031.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, neural speech synthesizers have achieved a high-quality synthesis for text-to-speech applications, but a real-time synthesis is possible only in the devices which have high memory and allow large computational complexity. In this work, we reduce the complexity of a speech synthesizer by reformulating the source-filter model of speech where the excitation signal is modeled as a sum of two signals. The first signal contains an impulse train that is computed from the pitch sequence. The second signal is modeled as white noise passed through a filter bank with frequency dependent gains. The parameters of the reformulated source-filter model are predicted using a neural network, referred to as SFNet. The network parameters are learnt by training the network using l(1)-error between the log Mel-spectrum of the predicted waveform and that of the ground-truth waveform. We demonstrate that there is a significant reduction in the memory and computational complexity compared to the state-of-the-art speaker independent neural speech synthesizer without any loss of the naturalness of the synthesized speech.
Keyword:
Neural vocoder
source-filter model
computational complexity
Mel-spectrum
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
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
分享收藏Bioanalytical Approaches for Characterizing Catabolism of Antibody–Drug Conjugates.png)
Bioanalysis
BioanalysisIF0
PREAI
分享收藏分享收藏GlotNet-A Raw Waveform Model for the Glottal Excitation in Statistical Parametric Speech Synthesis
PREAI
分享收藏分享收藏分享收藏
查看更多内容