DeepAI AI Chat
Log In Sign Up

Music Source Separation with Generative Flow

by   Ge Zhu, et al.
University of Rochester

Full supervision models for source separation are trained on mixture-source parallel data and have achieved superior performance in recent years. However, large-scale and naturally mixed parallel training data are difficult to obtain for music, and such models are difficult to adapt to mixtures with new sources. Source-only supervision models, in contrast, only require clean sources for training; They learn source models and then apply these models to separate the mixture.


Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity

Music source separation performance has greatly improved in recent years...

Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction

The state of the art in music source separation employs neural networks ...

Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision

Most music source separation systems require large collections of isolat...

A Style Transfer Approach to Source Separation

Training neural networks for source separation involves presenting a mix...

One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal

Single channel blind source separation (SCBSS) refers to separate multip...

Music Separation Enhancement with Generative Modeling

Despite phenomenal progress in recent years, state-of-the-art music sepa...

Danna-Sep: Unite to separate them all

Deep learning-based music source separation has gained a lot of interest...

Code Repositories


Open source code for the paper 'Music Source Separation with Generative Flow'

view repo