The growing popularity of generative music models underlines the need for perceptually
relevant, objective music quality metrics. The Frechet Audio Distance (FAD) is commonly …

This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge
(SDX'23). We provide a summary of the challenge setup and introduce the task of robust …

Audio super-resolution is a fundamental task that predicts high-frequency components for
low-resolution audio, enhancing audio quality in digital applications. Previous methods have …

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive
learning method for musical audio representations that captures the harmonic and rhythmic …

Deep learning-based methods have made significant achievements in music source
separation. However, obtaining good results while maintaining a low model complexity …

The Cadenza project aims to enhance the audio quality of music for individuals with hearing
loss. As part of this, the project is organizing the ICASSP SP Cadenza Challenge: Music …

We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for
controlling an autoregressive generative music transformer using classifier probes. These …

Neural upmixing, the task of generating immersive music with an increased number of
channels from fewer input channels, has been an active research area, with mono-to-stereo …

Despite significant recent progress across multiple subtasks of audio source separation, few
music source separation systems support separation beyond the four-stem vocals, drums …

In music source separation, a standard training data augmentation procedure is to create
new training samples by randomly combining instrument stems from different songs. These …