Related papers: Score-informed Music Source Separation: Improving …
The performance of deep learning models for music source separation heavily depends on training data quality. However, datasets are often corrupted by difficult-to-detect artifacts such as audio bleeding and label noise. Since the type and…
This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used…
Musical score following is the real-time mapping of a performance to corresponding locations in a musical score. Score following can be used in a variety of applications including automatic page turning and real-time accompaniment. This…
Universal source separation targets at separating the audio sources of an arbitrary mix, removing the constraint to operate on a specific domain like speech or music. Yet, the potential of universal source separation is limited because most…
Music source separation is a core task in music information retrieval which has seen a dramatic improvement in the past years. Nevertheless, most of the existing systems focus exclusively on the problem of source separation itself and…
Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore the separation ability of models. In this work, we reveal that…
Popular music is often composed of an accompaniment and a lead component, the latter typically consisting of vocals. Filtering such mixtures to extract one or both components has many applications, such as automatic karaoke and remixing.…
Music source separation (MSS) aims to extract individual instrument sources from their mixture. While most existing methods focus on the widely adopted four-stem separation setup (vocals, bass, drums, and other instruments), this approach…
Deep learning-based approaches to musical source separation are often limited to the instrument classes that the models are trained on and do not generalize to separate unseen instruments. To address this, we propose a few-shot musical…
Could we automatically derive the score of a piano accompaniment based on the audio of a pop song? This is the audio-to-symbolic arrangement problem we tackle in this paper. A good arrangement model should not only consider the audio…
Music creation is typically composed of two parts: composing the musical score, and then performing the score with instruments to make sounds. While recent work has made much progress in automatic music generation in the symbolic domain,…
I developed a neural audio codec model based on the residual quantized variational autoencoder architecture. I train the model on the Slakh2100 dataset, a standard dataset for musical source separation, composed of multi-track audio. The…
The Inaugural Music Source Restoration (MSR) Challenge targets the recovery of original, unprocessed stems from fully mixed and mastered music. Unlike conventional music source separation, MSR requires reversing complex production processes…
Music source separation represents the task of extracting all the instruments from a given song. Recent breakthroughs on this challenge have gravitated around a single dataset, MUSDB, only limited to four instrument classes. Larger datasets…
We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most representative audio source separation losses we identified, to…
Visual sound source separation aims at identifying sound components from a given sound mixture with the presence of visual cues. Prior works have demonstrated impressive results, but with the expense of large multi-stage architectures and…
We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder decoder architecture and takes as input the magnitude…
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…
We propose a method for the blind separation of sounds of musical instruments in audio signals. We describe the individual tones via a parametric model, training a dictionary to capture the relative amplitudes of the harmonics. The model…
Given the large number of new musical tracks released each year, automated approaches to plagiarism detection are essential to help us track potential violations of copyright. Most current approaches to plagiarism detection are based on…