Shiyin Kang

Phonetic posteriorgrams for many-to-one voice conversion without parallel data training

Lifa Sun, Kun Li, Hao Wang et al. · 2016 · 314 citations

Engineering, Parallel Training Data, Speech Recognition +20

Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks

Lifa Sun, Shiyin Kang, Kun Li et al. · 2015 · 273 citations

Engineering, Speech Recognition, Natural Language Processing +16

Multi-distribution deep belief network for speech synthesis

Shiyin Kang, Xiaojun Qian, Helen Meng · 2013 · 105 citations

Engineering, Machine Learning, Speech Recognition +17

FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement

Jun Chen, Zilin Wang, Deyi Tuo et al. · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022 · 104 citations

Engineering, Speech Enhancement, Deep Noise Suppression +16

DurIAN: Duration Informed Attention Network For Multimodal Synthesis

Chengzhu Yu, Heng Lu, Na Hu et al. · arXiv (Cornell University) · 2019 · 94 citations · Full text

Artificial Intelligence, Engineering, Multimodal Learning +23