Model weights and pre-processed audio files for Diffiner
Lists
Only you see this
Abstract
This repository contains the pre-trained model weights for Diffiner proposed in the paper Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement by Sony. Furthermore, to run Diffiner same as our paper, the preceding results processed by DCUnet are provided here. More information about Diffiner including our codes is available in https://github.com/sony/diffiner.
BibTeX
@inproceedings{sawata2023model,
author = {Ryosuke Sawata and Naoki Murata and Yuhta Takida and Toshimitsu Uesaka and Takashi Shibuya and Shusuke Takahashi and Yuki Mitsufuji},
title = {{Model weights and pre-processed audio files for Diffiner}},
booktitle = {Zenodo},
year = {2023},
doi = {10.5281/zenodo.7988789},
}Loading related content...