P
Peng Liu
Researcher at Tencent
Publications - 13
Citations - 362
Peng Liu is an academic researcher from Tencent. The author has contributed to research in topics: Speech synthesis & Word error rate. The author has an hindex of 7, co-authored 13 publications receiving 254 citations. Previous affiliations of Peng Liu include Tsinghua University.
Papers
More filters
Posted Content
DurIAN: Duration Informed Attention Network For Multimodal Synthesis.
Chengzhu Yu,Heng Lu,Na Hu,Meng Yu,Chao Weng,Kun Xu,Peng Liu,Deyi Tuo,Shiyin Kang,Guangzhi Lei,Dan Su,Dong Yu +11 more
TL;DR: It is shown that DurIAN could generate highly natural speech that is on par with current state of the art end-to-end systems, while at the same time avoid word skipping/repeating errors in those systems.
Proceedings ArticleDOI
A deep recurrent approach for acoustic-to-articulatory inversion
TL;DR: Experimental results indicate that recurrent model can produce more accurate predictions for acoustic-to-articulatory inversion than deep neural network having fixed-length context window.
Proceedings ArticleDOI
DurIAN: Duration Informed Attention Network for Speech Synthesis.
Chengzhu Yu,Heng Lu,Na Hu,Meng Yu,Chao Weng,Kun Xu,Peng Liu,Deyi Tuo,Shiyin Kang,Guangzhi Lei,Dan Su,Dong Yu +11 more
TL;DR: It is shown that proposed DurIAN system could generate highly natural speech that is on par with current state of the art end-to-end systems, while being robust and stable at the same time.
Proceedings ArticleDOI
Voice activity detection using visual information
Peng Liu,Zuoying Wang +1 more
TL;DR: The experiments show that using visual information based VAD, prominent reduction in frame error rate is achieved, and the audio-visual stream can be segmented into sentences for recognition much more precisely, compared to the frame-energy based approach in the clean audio case.
Proceedings ArticleDOI
Learning cross-lingual information with multilingual BLSTM for speech synthesis of low-resource languages
TL;DR: A multilingual BLSTM that shares hidden layers across different languages and a specific training approach that can best utilize the training data from both the auxiliary and target languages are proposed.