Related papers: SynthSOD: Developing an Heterogeneous Dataset for …

A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to…

This paper introduces a novel dataset for polyphonic sound event detection in urban sound monitoring use-cases. Based on isolated sounds taken from the FSD50k dataset, 20,000 polyphonic soundscapes are synthesized with sounds being randomly…

We propose a visually conditioned music remixing system by incorporating deep visual and audio models. The method is based on a state of the art audio-visual source separation model which performs music instrument source separation with…

In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation models on synthetic datasets, while the performance of state-of-the-art techniques on in-the-wild…

Music representation learning is central to music information retrieval and generation. While recent advances in multimodal learning have improved alignment between text and audio for tasks such as cross-modal music retrieval, text-to-music…

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…

We propose a generative framework for multi-track music source separation (MSS) that reformulates the task as conditional discrete token generation. Unlike conventional approaches that directly estimate continuous signals in the time or…

Music mixing traditionally involves recording instruments in the form of clean, individual tracks and blending them into a final mixture using audio effects and expert knowledge (e.g., a mixing engineer). The automation of music production…

Chord progressions encapsulate important information about music, pertaining to its structure and conveyed emotions. They serve as the backbone of musical composition, and in many cases, they are the sole information required for a musician…

This work present a music dataset named MusicTM-Dataset, which is utilized in improving the representation learning ability of different types of cross-modal retrieval (CMR). Little large music dataset including three modalities is…

Recent progress in deep learning has enabled many advances in sound separation and visual scene understanding. However, extracting sound sources which are apparent in natural videos remains an open problem. In this work, we present…

Despite its potential, AI advances in music education are hindered by proprietary systems that limit the democratization of technology in this domain. In particular, AI-driven music difficulty adjustment is especially promising, as…

The lack of a publicly-available large-scale and diverse dataset has long been a significant bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing Voice Conversion (SVC). To tackle this problem, we present…

In this paper we propose a conditioned UNet for Music Source Separation (MSS). MSS is generally performed by multi-output neural networks, typically UNets, with each output representing a particular stem from a predefined instrument…

Computational analysis of performed music is a key component of music information research, as performance shapes much of the music we hear. Music performance analysis studies the acoustic variations introduced by performers and how these…

With the popularity of cellular phones, events are often recorded by multiple devices from different locations and shared on social media. Several different recordings could be found for many events. Such recordings are usually noisy, where…

Music source separation is the task of isolating the instrumental tracks from a music song. Despite its spectacular recent progress, the trend towards more complex architectures and training protocols exacerbates reproducibility issues. The…

Deep Neural Network-based source separation methods usually train independent models to optimize for the separation of individual sources. Although this can lead to good performance for well-defined targets, it can also be computationally…

Generative models for audio-conditioned dance motion synthesis map music features to dance movements. Models are trained to associate motion patterns to audio patterns, usually without an explicit knowledge of the human body. This approach…

Recent years have witnessed the success of deep learning on the visual sound separation task. However, existing works follow similar settings where the training and testing datasets share the same musical instrument categories, which to…