Related papers: Music Separation Enhancement with Generative Model…

Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical…

The integration of additional side information to improve music source separation has been investigated numerous times, e.g., by adding features to the input or by adding learning targets in a multi-task learning scenario. These approaches,…

With the recent advancements of data driven approaches using deep neural networks, music source separation has been formulated as an instrument-specific supervised problem. While existing deep learning models implicitly absorb the spatial…

Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts violate common linear-mixture assumptions. This technical…

In this paper, we propose a simple yet effective method for multiple music source separation using convolutional neural networks. Stacked hourglass network, which was originally designed for human pose estimation in natural images, is…

Music Source Restoration (MSR) extends source separation to realistic settings where signals undergo production effects (equalization, compression, reverb) and real-world degradations, with the goal of recovering the original unprocessed…

We propose a new method for separating superimposed sources using diffusion-based generative models. Our method relies only on separately trained statistical priors of independent sources to establish a new objective function guided by…

Deep neural networks have shown promise for music audio signal processing applications, often surpassing prior approaches, particularly as end-to-end models in the waveform domain. Yet results to date have tended to be constrained by low…

Music source separation in the time-frequency domain is commonly achieved by applying a soft or binary mask to the magnitude component of (complex) spectrograms. The phase component is usually not estimated, but instead copied from the…

Objective assessment of audio source-separation systems still mismatches subjective human perception, especially when interference from competing talkers and distortion of the target signal interact. We introduce Perceptual Separation (PS)…

Audio processing methods based on deep neural networks are typically trained at a single sampling frequency (SF). To handle untrained SFs, signal resampling is commonly employed, but it can degrade performance, particularly when the input…

Impressive progress in neural network-based single-channel speech source separation has been made in recent years. But those improvements have been mostly reported on anechoic data, a situation that is hardly met in practice. Taking the…

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks. With the push to acquire larger datasets to improve MSS performance, the inevitability of encountering…

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation…

The "cocktail party" problem of fully separating multiple sources from a single channel audio waveform remains unsolved. Current biological understanding of neural encoding suggests that phase information is preserved and utilized at every…

Source separation models either work on the spectrogram or waveform domain. In this work, we show how to perform end-to-end hybrid source separation, letting the model decide which domain is best suited for each source, and even combining…

Typical methods for binaural source separation consider only the direct sound as the target signal in a mixture. However, in most scenarios, this assumption limits the source separation performance. It is well known that the early…

Generating multi-instrument music from symbolic music representations is an important task in Music Information Retrieval (MIR). A central but still largely unsolved problem in this context is musically and acoustically informed control in…

With the rapid advancement of generative audio models, distinguishing between human-composed and generated music is becoming increasingly challenging. As a response, models for detecting fake music have been proposed. In this work, we…

Systems for synthesizer sound matching, which automatically set the parameters of a synthesizer to emulate an input sound, have the potential to make the process of synthesizer programming faster and easier for novice and experienced…