no code implementations • 21 Feb 2022 • Jingdong Li, Yuanyuan Zhu, Dawei Luo, Yun Liu, Guohui Cui, Zhaoxia Li
This paper described the PCG-AIID system for L3DAS22 challenge in Task 1: 3D speech enhancement in office reverberant environment.
1 code implementation • 11 Nov 2021 • Yihui Fu, Yun Liu, Jingdong Li, Dawei Luo, Shubo Lv, Yukai Jv, Lei Xie
Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation.
no code implementations • 2 Feb 2020 • Jingdong Li, HUI ZHANG, Xueliang Zhang, Changliang Li
We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks.
no code implementations • 7 Nov 2019 • Rui Liu, Berrak Sisman, Jingdong Li, Feilong Bao, Guanglai Gao, Haizhou Li
We first train a Tacotron2-based TTS model by always providing natural speech frames to the decoder, that serves as a teacher model.