Related papers: Music Source Separation in the Waveform Domain

Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating mixtures of arbitrary sounds of different types, a task we…

We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly…

In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is…

Time-Frequency (TF) dual-path models are currently among the best performing audio source separation network architectures, achieving state-of-the-art performance in speech enhancement, music source separation, and cinematic audio source…

Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures…

Music is often experienced as a progression of concurrent streams of notes, or voices. The degree to which this happens depends on the position along a voice-leading continuum, ranging from monophonic, to homophonic, to polyphonic, which…

Deep learning-based works for singing voice separation have performed exceptionally well in the recent past. However, most of these works do not focus on allowing users to interact with the model to improve performance. This can be crucial…

Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods. While most musical source separation…

Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…

Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative…

This work addresses the problem of multichannel source separation combining two powerful approaches, multichannel spectral factorization with recent monophonic deep-learning (DL) based spectrum inference. Individual source spectra at…

A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have developed algorithms that predict the compatibility of audio elements. Prior work has…

Cinematic audio source separation (CASS), as a problem of extracting the dialogue, music, and effects stems from their mixture, is a relatively new subtask of audio source separation. To date, only one publicly available dataset exists for…

While diffusion models are best known for their performance in generative tasks, they have also been successfully applied to many other tasks, including audio source separation. However, current generative approaches to music source…

The analysis of the structure of musical pieces is a task that remains a challenge for Artificial Intelligence, especially in the field of Deep Learning. It requires prior identification of structural boundaries of the music pieces. This…

This paper introduces a multi-stage self-directed framework designed to address the spatial semantic segmentation of sound scene (S5) task in the DCASE 2025 Task 4 challenge. This framework integrates models focused on three distinct tasks:…

Singing Voice Separation (SVS) tries to separate singing voice from a given mixed musical signal. Recently, many U-Net-based models have been proposed for the SVS task, but there were no existing works that evaluate and compare various…

Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaural singing voice separation are obtained with deep learning…

Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets,…

Recent work has shown that recurrent neural networks can be trained to separate individual speakers in a sound mixture with high fidelity. Here we explore convolutional neural network models as an alternative and show that they achieve…