RemixIT: Continual self-training of speech enhancement models via
bootstrapped remixing

RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing

17 February 2022

Efthymios Tzinis

Yossi Adi

Paris Smaragdis

Papers citing "RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing"

10 / 10 papers shown

Title
Unsupervised Blind Speech Separation with a Diffusion Prior Zhongweiyang Xu Xulin Fan Zhong-Qiu Wang Xilin Jiang Romit Roy Choudhury DiffM 40 0 0 08 May 2025
DeWinder: Single-Channel Wind Noise Reduction using Ultrasound Sensing Kuang Yuan Shuo Han Swarun Kumar Bhiksha Raj 24 2 0 10 Sep 2024
Deep learning-based denoising streamed from mobile phones improves speech-in-noise understanding for hearing aid users P. U. Diehl Hannes Zilly Felix Sattler Y. Singer Kevin Kepp ... Paul Meyer-Rachner A. Pudszuhn V. Hofmann M. Vormann Elias Sprengel 29 3 0 22 Aug 2023
Deep neural network techniques for monaural speech enhancement: state of the art analysis P. Ochieng 28 21 0 01 Dec 2022
Self-Remixing: Unsupervised Speech Separation via Separation and Remixing Kohei Saijo Tetsuji Ogawa SSL 17 11 0 18 Nov 2022
Exploring WavLM on Speech Enhancement Hyungchan Song Sanyuan Chen Zhuo Chen Yu-Huan Wu Takuya Yoshioka M. Tang Jong Won Shin Shujie Liu 8 16 0 18 Nov 2022
Speech separation with large-scale self-supervised learning Zhuo Chen Naoyuki Kanda Jian Wu Yu-Huan Wu Xiaofei Wang Takuya Yoshioka Jinyu Li S. Sivasankaran Sefik Emre Eskimez 17 13 0 09 Nov 2022
Analysis of Noisy-target Training for DNN-based speech enhancement Takuya Fujimura T. Toda 27 4 0 02 Nov 2022
On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training Jisi Zhang Catalin Zorila R. Doddipatla Jon Barker 22 4 0 03 May 2022
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results Antti Tarvainen Harri Valpola OOD MoMe 244 1,275 0 06 Mar 2017