A survey of audio enhancement algorithms for music, speech, bioacoustics, biomedical, industrial and environmental sounds by image U-Net

S Gul, MS Khan - IEEE Access, 2023 - ieeexplore.ieee.org
The recent surge in the use of Deep Neural Networks (DNNs) has also made its mark in the
field of Audio Enhancement (AE), providing much better quality than the classical methods …

CWS-PResUNet: Music source separation with channel-wise subband phase-aware resunet

H Liu, Q Kong, J Liu - arXiv preprint arXiv:2112.04685, 2021 - arxiv.org
Music source separation (MSS) shows active progress with deep learning models in recent
years. Many MSS models perform separations on spectrograms by estimating bounded ratio …

[PDF][PDF] Hierarchical Musical Instrument Separation.

E Manilow, G Wichern, J Le Roux - ISMIR, 2020 - program.ismir2020.net
Many sounds that humans encounter are hierarchical in nature; a piano note is one of many
played during a performance, which is one of many instruments in a band, which might be …

Channel-wise subband input for better voice and accompaniment separation on high resolution music

H Liu, L Xie, J Wu, G Yang - arXiv preprint arXiv:2008.05216, 2020 - arxiv.org
This paper presents a new input format, channel-wise subband input (CWS), for
convolutional neural networks (CNN) based music source separation (MSS) models in the …

Semi-supervised singing voice separation with noisy self-training

Z Wang, R Giri, U Isik, JM Valin… - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
Recent progress in singing voice separation has primarily focused on supervised deep
learning methods. However, the scarcity of ground-truth data with clean musical sources has …

Improved singing voice separation with chromagram-based pitch-aware remixing

S Yuan, Z Wang, U Isik, R Giri, JM Valin… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Singing voice separation aims to separate music into vocals and accompaniment
components. One of the major constraints for the task is the limited amount of training data …

A cappella: Audio-visual singing voice separation

JF Montesinos, VS Kadandale, G Haro - arXiv preprint arXiv:2104.09946, 2021 - arxiv.org
The task of isolating a target singing voice in music videos has useful applications. In this
work, we explore the single-channel singing voice separation problem from a multimodal …

A novel U-Net with dense block for drum signal separation from polyphonic music signal mixture

E Vinitha George, VP Devassia - Signal, Image and Video Processing, 2023 - Springer
Deep neural network algorithms have shown promising results for music source signal
separation. Most existing methods rely on deep networks, where billions of parameters need …

Single channel speech enhancement by colored spectrograms

S Gul, MS Khan, M Fazeel - arXiv preprint arXiv:2310.17142, 2023 - arxiv.org
Speech enhancement concerns the processes required to remove unwanted background
sounds from the target speech to improve its quality and intelligibility. In this paper, a novel …

Audio denoising for robust audio fingerprinting

K Akesbi - arXiv preprint arXiv:2212.11277, 2022 - arxiv.org
Music discovery services let users identify songs from short mobile recordings. These
solutions are often based on Audio Fingerprinting, and rely more specifically on the …