Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm

22 October 2020

Papers citing "Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn's Algorithm"

5 / 5 papers shown

Title
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing David Perera Victor Letzelter Théo Mariotte Adrien Cortés Mickaël Chen S. Essid Ga¨el Richard 74 2 0 20 Jan 2025
Deep neural network techniques for monaural speech enhancement: state of the art analysis P. Ochieng 30 21 0 01 Dec 2022
Location-based training for multi-channel talker-independent speaker separation H. Taherian Ke Tan DeLiang Wang 27 10 0 08 Oct 2021
Many-Speakers Single Channel Speech Separation with Optimal Permutation Training Shaked Dovrat Eliya Nachmani Lior Wolf VLM 6 21 0 18 Apr 2021
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation Jing-jing Chen Qi-rong Mao Dong Liu 62 280 0 28 Jul 2020