相关论文: Discogs-VI: A Musical Version Identification Datas…

Version identification (VI) systems now offer accurate and scalable solutions for detecting different renditions of a musical composition, allowing the use of these systems in industrial applications and throughout the wider music…

In this article, we aim to provide a review of the key ideas and approaches proposed in 20 years of scientific literature around musical version identification (VI) research and connect them to current practice. For more than a decade, VI…

Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three…

Version identification (VI) has seen substantial progress over the past few years. On the one hand, the introduction of the metric learning paradigm has favored the emergence of scalable yet accurate VI systems. On the other hand, using…

The setlist identification (SLI) task addresses a music recognition use case where the goal is to retrieve the metadata and timestamps for all the tracks played in live music events. Due to various musical and non-musical changes in live…

We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions…

The goal of this paper is twofold. First, we introduce DALI, a large and rich multimodal dataset containing 5358 audio tracks with their time-aligned vocal melody notes and lyrics at four levels of granularity. The second goal is to explain…

A large-scale dataset is essential for training a well-generalized deep-learning model. Most such datasets are collected via scraping from various internet sources, inevitably introducing duplicated data. In the symbolic music domain, these…

Generative models guided by text prompts are increasingly becoming more popular. However, no text-to-MIDI models currently exist due to the lack of a captioned MIDI dataset. This work aims to enable research that combines LLMs with symbolic…

Recent advances in AI-based music generation have focused heavily on text-conditioned models, with less attention given to reference-based generation such as song adaptation. To support this line of research, we introduce LargeSHS, a…

In this document, we introduce a new dataset designed for training machine learning models of symbolic music data. Five datasets are provided, one of which is from a newly collected corpus of 20K midi files. We describe our preprocessing…

The version identification (VI) task deals with the automatic detection of recordings that correspond to the same underlying musical piece. Despite many efforts, VI is still an open problem, with much room for improvement, specially with…

Neural models are one of the most popular approaches for music generation, yet there aren't standard large datasets tailored for learning music directly from game data. To address this research gap, we introduce a novel dataset named…

Musical dynamics form a core part of expressive singing voice performances. However, automatic analysis of musical dynamics for singing voice has received limited attention partly due to the scarcity of suitable datasets and a lack of clear…

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music,…

Today, comprehensive evaluation of large-scale machine learning models is possible thanks to the open datasets produced using crowdsourcing, such as SQuAD, MS COCO, ImageNet, SuperGLUE, etc. These datasets capture objective responses,…

We present a new large-scale emotion-labeled symbolic music dataset consisting of 12k MIDI songs. To create this dataset, we first trained emotion classification models on the GoEmotions dataset, achieving state-of-the-art results with a…

Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database.…

At the core of many important machine learning problems faced by online streaming services is a need to model how users interact with the content they are served. Unfortunately, there are no public datasets currently available that enable…

One of the main limitations in the field of audio signal processing is the lack of large public datasets with audio representations and high-quality annotations due to restrictions of copyrighted commercial music. We present Melon Playlist…