Adversarial Permutation Invariant Training for Universal Sound
Separation

v1v2 (latest)

Adversarial Permutation Invariant Training for Universal Sound Separation

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022

21 October 2022

Emilian Postolache

Santiago Pascual

ArXiv (abs)PDF HTML

Papers citing "Adversarial Permutation Invariant Training for Universal Sound Separation"

7 / 7 papers shown

Title
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation Zihan Zhang Xize Cheng Zhennan Jiang Dongjie Fu Jingyuan Chen Zhou Zhao Tao Jin 74 0 0 12 Oct 2025
Fast Text-to-Audio Generation with Adversarial Post-Training Cheng-i Wang Zach Evans Zack Zukowski Josiah Taylor CJ Carr ... Adnan Al-Sinan Gian Marco Iodice Julian McAuley Taylor Berg-Kirkpatrick Jordi Pons 492 8 0 13 May 2025
Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion ModelsIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 Tornike Karchkhadze M. Izadi Shlomo Dubnov DiffM 329 13 0 31 Dec 2024
Improving Source Extraction with Diffusion and Consistency Models Tornike Karchkhadze M. Izadi Shuo Zhang DiffM 310 1 0 09 Dec 2024
GASS: Generalizing Audio Source Separation with Large-scale DataIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 Jordi Pons Xiaoyu Liu Santiago Pascual Joan Serrà 181 21 0 29 Sep 2023
Multi-Source Diffusion Models for Simultaneous Music Generation and SeparationInternational Conference on Learning Representations (ICLR), 2023 Giorgio Mariani Irene Tallini Emilian Postolache Michele Mancusi Luca Cosmo Emanuele Rodolà DiffM 523 65 0 04 Feb 2023
Latent Autoregressive Source SeparationAAAI Conference on Artificial Intelligence (AAAI), 2023 Emilian Postolache Giorgio Mariani Michele Mancusi Andrea Santilli Luca Cosmo Emanuele Rodolà BDL DRL 155 13 0 09 Jan 2023