Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Le, Xiaohuai"'
Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model
Autor:
Le, Xiaohuai, Lei, Tong, Chen, Li, Guo, Yiqing, He, Chao, Chen, Cheng, Xia, Xianjun, Gao, Hua, Xiao, Yijian, Ding, Piao, Song, Shenyi, Lu, Jing
With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic retrieval. Th
Externí odkaz:
http://arxiv.org/abs/2306.00812
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine transformat
Externí odkaz:
http://arxiv.org/abs/2302.09953
Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational cost. Typic
Externí odkaz:
http://arxiv.org/abs/2207.11108
Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated strategies, i
Externí odkaz:
http://arxiv.org/abs/2206.14524
The dual-path RNN (DPRNN) was proposed to more effectively model extremely long sequences for speech separation in the time domain. By splitting long sequences to smaller chunks and applying intra-chunk and inter-chunk RNNs, the DPRNN reached promisi
Externí odkaz:
http://arxiv.org/abs/2107.05429