Related papers: Don't Separate, Learn to Remix: End-to-End Neural …

Sampling, the practice of reusing recorded music or sounds from another source in a new work, is common in popular music genres like hip-hop and rap. Numerous services have emerged that allow users to identify connections between samples…

In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference…

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of…

The sources separated by most single channel audio source separation techniques are usually distorted and each separated source contains residual signals from the other sources. To tackle this problem, we propose to enhance the separated…

Music source separation (MSS) is the task of separating a music piece into individual sources, such as vocals and accompaniment. Recently, neural network based methods have been applied to address the MSS problem, and can be categorized…

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model…

Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high. Although there exist ways for model pruning or distillation, it is typically…

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…

Music segmentation refers to the dual problem of identifying boundaries between, and labeling, distinct music segments, e.g., the chorus, verse, bridge etc. in popular music. The performance of a range of music segmentation algorithms has…

Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for mixing style transfer are limited in that they often…

State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain. However, these methods are…

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its…

Sounds provide rich semantics, complementary to visual data, for many tasks. However, in practice, sounds from multiple sources are often mixed together. In this paper we propose a novel framework, referred to as MinusPlus Network (MP-Net),…

Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…

End-to-end learning models have demonstrated a remarkable capability in performing speech segregation. Despite their wide-scope of real-world applications, little is known about the mechanisms they employ to group and consequently segregate…

Existing work on pitch and timbre disentanglement has been mostly focused on single-instrument music audio, excluding the cases where multiple instruments are presented. To fill the gap, we propose DisMix, a generative framework in which…

Despite the recent success of speech separation models, they fail to separate sources properly while facing different sets of people or noisy environments. To tackle this problem, we proposed to apply meta-learning to the speech separation…

Many recent source separation systems are designed to separate a fixed number of sources out of a mixture. In the cases where the source activation patterns are unknown, such systems have to either adjust the number of outputs or to…

Audio separation in real-world scenarios, where mixtures contain a variable number of sources, presents significant challenges due to limitations of existing models, such as over-separation, under-separation, and dependence on predefined…

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency…