Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Han, Runduo"'
The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model, Distil-DCCRN,
Externí odkaz:
http://arxiv.org/abs/2408.04267
Autor:
Han, Runduo, Yan, Xiaopeng, Xu, Weiming, Guo, Pengcheng, Sun, Jiayao, Wang, He, Lu, Quan, Jiang, Ning, Xie, Lei
This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts different
Externí odkaz:
http://arxiv.org/abs/2401.03697
Autor:
Xu, Weiming, Chen, Zhouxuan, Tan, Zhili, Lv, Shubo, Han, Runduo, Zhou, Wenjiang, Zhao, Weifeng, Xie, Lei
A typical neural speech enhancement (SE) approach mainly handles speech and noise mixtures, which is not optimal for singing voice enhancement scenarios. Music source separation (MSS) models treat vocals and various accompaniment components equally,
Externí odkaz:
http://arxiv.org/abs/2310.04369
Autor:
Liu, Mingshuai, Lv, Shubo, Zhang, Zihan, Han, Runduo, Hao, Xiang, Xia, Xianjun, Chen, Li, Xiao, Yijian, Xie, Lei
In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech
Externí odkaz:
http://arxiv.org/abs/2303.07621
Publikováno v:
In Information Sciences February 2025 690