相关论文: MusPy: A Toolkit for Symbolic Music Generation
Understanding how machine learning models respond to distributional shifts is a key research challenge. Mazes serve as an excellent testbed due to varied generation algorithms offering a nuanced platform to simulate both subtle and…
Musical expression requires control of both what notes are played, and how they are performed. Conventional audio synthesizers provide detailed expressive controls, but at the cost of realism. Black-box neural audio synthesis and…
Despite progress in controllable symbolic music generation, data scarcity remains a challenge for certain control modalities. Composer-style music generation is a prime example, as only a few pieces per composer are available, limiting the…
We present the first public version (v0.2) of the open-source and community-developed Python package, Astropy. This package provides core astronomy-related functionality to the community, including support for domain-specific file formats…
Deep Learning models have shown very promising results in automatically composing polyphonic music pieces. However, it is very hard to control such models in order to guide the compositions towards a desired goal. We are interested in…
Molecular dynamics simulations play an increasingly important role in the rational design of (nano)-materials and in the study of biomacromolecules. However, generating input files and realistic starting coordinates for these simulations is…
Music datasets play a crucial role in advancing research in machine learning for music. However, existing music datasets suffer from limited size, accessibility, and lack of audio resources. To address these shortcomings, we present…
A curated dataset of Guitar Pro tablature files (.gp5 format), tailored for tasks involving guitar music generation, sequence modeling, and performance-aware learning is provided. The dataset is derived from MIDI notes in MAESTRO and…
Synthetic images created by generative models increase in quality and expressiveness as newer models utilize larger datasets and novel architectures. Although this photorealism is a positive side-effect from a creative standpoint, it…
Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains. However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music.…
As the volume of video content on the internet grows rapidly, finding a suitable soundtrack remains a significant challenge. This thesis presents EMSYNC (EMotion and SYNChronization), a fast, free, and automatic solution that generates…
Ensuring the reproducibility of scientific work is crucial as it allows the consistent verification of scientific claims and facilitates the advancement of knowledge by providing a reliable foundation for future research. However,…
This paper proposes a software repository model together with associated tooling and consists of several complex, open-source GUI driven applications ready to be used in empirical software research. We start by providing the rationale for…
Learning the violin is harder than it looks. Unlike piano keys or guitar frets, the violin neck has no markings at all, so a beginner cannot tell by looking where to place each finger. MusicSynth is an open-source web tool that tries to fix…
Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus…
Graphs can be leveraged to model polyphonic multitrack symbolic music, where notes, chords and entire sections may be linked at different levels of the musical hierarchy by tonal and rhythmic relationships. Nonetheless, there is a lack of…
The synthpop package for R https://www.synthpop.org.uk provides tools to allow data custodians to create synthetic versions of confidential microdata that can be distributed with fewer restrictions than the original. The synthesis can be…
Discrete representation learning has shown promising results across various domains, including generation and understanding in image, speech and language. Inspired by these advances, we propose MuseTok, a tokenization method for symbolic…
Deep learning-based probabilistic models of musical data are producing increasingly realistic results and promise to enter creative workflows of many kinds. Yet they have been little-studied in a performance setting, where the results of…
We introduce CLaMP: Contrastive Language-Music Pre-training, which learns cross-modal representations between natural language and symbolic music using a music encoder and a text encoder trained jointly with a contrastive loss. To pre-train…