Mixup-breakdown: a consistency training method for improving generalization of speech separation models

28 October 2019

Papers citing "Mixup-breakdown: a consistency training method for improving generalization of speech separation models"

7 / 7 papers shown

Title
TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation Zhongqiu Wang Samuele Cornell Shukjae Choi Younglo Lee Byeonghak Kim Shinji Watanabe 24 119 0 22 Nov 2022
Heterogeneous Separation Consistency Training for Adaptation of Unsupervised Speech Separation Jiangyu Han Yanhua Long 20 6 0 23 Apr 2022
MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training Ertuğ Karamatlı S. Kırbız SSL 30 9 0 08 Feb 2022
Towards Domain-Agnostic Contrastive Learning Vikas Verma Minh-Thang Luong Kenji Kawaguchi Hieu H. Pham Quoc V. Le SSL 15 115 0 09 Nov 2020
Wavesplit: End-to-End Speech Separation by Speaker Clustering Neil Zeghidour David Grangier VLM 23 261 0 20 Feb 2020
Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures J. Wang Jie Chen Dan Su Lianwu Chen Meng Yu Y. Qian Dong Yu 38 90 0 24 Jul 2018
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction Zhong-Qiu Wang Jonathan Le Roux DeLiang Wang J. Hershey 90 123 0 26 Apr 2018