Differentiable digital signal processing mixture model for synthesis parameter extraction from mixture of harmonic sounds
A differentiable digital signal processing (DDSP) autoencoder is a musical sound
synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It …
synthesizer that combines a deep neural network (DNN) and spectral modeling synthesis. It …
Unsupervised music source separation using differentiable parametric source models
K Schulze-Forster, G Richard, L Kelley… - … on Audio, Speech …, 2023 - ieeexplore.ieee.org
Supervised deep learning approaches to underdetermined audio source separation achieve
state-of-the-art performance but require a dataset of mixtures along with their corresponding …
state-of-the-art performance but require a dataset of mixtures along with their corresponding …
Location as supervision for weakly supervised multi-channel source separation of machine sounds
R Falcon-Perez, G Wichern… - 2023 IEEE Workshop …, 2023 - ieeexplore.ieee.org
In this work, we are interested in learning a model to separate sources that cannot be
recorded in isolation, such as parts of a machine that must run simultaneously in order for …
recorded in isolation, such as parts of a machine that must run simultaneously in order for …
Jointist: Joint learning for multi-instrument transcription and its applications
In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is
capable of transcribing, recognizing, and separating multiple musical instruments from an …
capable of transcribing, recognizing, and separating multiple musical instruments from an …
Jointist: Simultaneous improvement of multi-instrument transcription and music source separation via joint training
In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is
capable of transcribing, recognizing, and separating multiple musical instruments from an …
capable of transcribing, recognizing, and separating multiple musical instruments from an …
Source separation by steering pretrained music models
We showcase a method that repurposes deep models trained for music generation and
music tagging for audio source separation, without any retraining. An audio generation …
music tagging for audio source separation, without any retraining. An audio generation …
Unsupervised source separation by steering pretrained music models
We showcase an unsupervised method that repurposes deep models trained for music
generation and music tagging for audio source separation, without any retraining. An audio …
generation and music tagging for audio source separation, without any retraining. An audio …
MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation
H Wei, Y Jun, R Zhang, Q Dai, Y Chen - ACM Multimedia 2024 - openreview.net
Music source separation and pitch estimation are two vital tasks in music information
retrieval. Typically, the input of pitch estimation is obtained from the output of music source …
retrieval. Typically, the input of pitch estimation is obtained from the output of music source …
Learning source-aware representations of music in a discrete latent space
J Kim, YS Jeong, W Choi, J Chung, S Jung - arXiv preprint arXiv …, 2021 - arxiv.org
In recent years, neural network based methods have been proposed as a method that
cangenerate representations from music, but they are not human readable and hardly …
cangenerate representations from music, but they are not human readable and hardly …
[PDF][PDF] Falcon-Perez, Ricardo; Wichern, Gordon; Germain, Francois G.; Le Roux, Jonathan Location as Supervision for Weakly Supervised Multi-Channel Source …
R Falcon-Perez - research.aalto.fi
In this work, we are interested in learning a model to separate sources that cannot be
recorded in isolation, such as parts of a machine that must run simultaneously in order for …
recorded in isolation, such as parts of a machine that must run simultaneously in order for …