论文地址:用于端到端语音增强的卷积递归神经网络 论文代码:https://github.com/aleXiehta/WaveCRN 引用格式:Hsieh T A, Wang H M, Lu X, et al. WaveCRN: An efficient convolutional recurrent neural network for end-to-end speech enhancement[J]. IEEE Signal Processing Letters, 2020, 27: 2149
Application of deep learning methods in speech enhancement 语音增强中的深度学习应用 按: 本文是DNS,AEC,PLC等国际级语音竞赛的主办方--Microsoft Research Labs音频与声学研究组(Audio and Acoustics Research Group)于2021年发表的Sound capture and speech enhancement for speech-enabled devices中节选的一章,总
基于孪生卷积网络(Siamese CNN)和短时约束度量联合学习的tracklet association方法 Siamese CNN Temporally Constrained Metrics Tracklet Association MTT MOT 读 'B. Wang, L. Wang, et.al. Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association[j],