JazzSAMBA：用于现场音乐模型的爵士标准曲同步与异步多遍乐队音频数据集
JazzSAMBA: A Synchronous and Asynchronous Multi-take Band Audio Dataset of Jazz Standards for Live Music Models
浏览论文内容
中文总结 AI 辅助
针对爵士乐缺乏高质量多轨数据集的问题，提出JazzSAMBA，首个含同步与异步录音的爵士标准曲多轨数据集，支持伴奏生成、源分离等任务。
中文摘要 AI 辅助
机器学习在音乐任务上取得了显著进展，既作为辅助工具，也作为创意伙伴。然而，大多数系统在强调流行和摇滚的多轨语料库上训练。爵士乐以即兴演奏为核心实践，仍然缺乏一个注释良好的、关于标准曲的干净分轨组合录音语料库。我们引入JazzSAMBA（爵士同步与异步多遍乐队音频）来填补这一空白：这是首个原始录制的爵士组合多轨标准曲数据集，包含异步（配音）和同步（现场合奏）两种协议，由音乐家选择的首选和备用录音版本，以及针对小节、和弦、段落和独奏者的定时注释。JazzSAMBA涵盖了八位音乐家演奏的76首标准曲，涉及鼓、贝斯、钢琴、小号和萨克斯，提供分轨音频、混音和MIDI。它可以支持基于图表条件的伴奏、组合源分离和形式感知的音乐信息检索。我们在两个任务上展示了该数据集：一个爵士组合源分离基线和一项基于图表条件的伴奏消融研究。数据集、代码和样本均链接自项目演示页面。
英文摘要
Machine learning has made strong progress on music tasks, both as assistive tools and as creative partners. However, most systems train on multitrack corpora that emphasize pop and rock. Jazz, with improvisation at the core of its practice, still lacks a well-annotated corpus of clean per-stem combo recordings on standards. We introduce JazzSAMBA (Jazz Synchronous and Asynchronous Multi-take Band Audio) to fill this gap: the first originally recorded jazz-combo multitrack dataset of standards with asynchronous (overdubbed) and synchronous (live ensemble) protocols, preferred and alternate takes chosen by the musicians, and timed annotations for bars, chords, sections, and soloists. JazzSAMBA covers 76 standards by eight musicians on drums, bass, piano, trumpet, and saxophone, with per-stem audio, mixtures, and MIDI. It can support chart-conditioned accompaniment, combo source separation, and form-aware music information retrieval. We demonstrate the dataset on two tasks: a jazz combo source-separation baseline and a chart-conditioned accompaniment ablation. The dataset, code, and samples are linked from the project demo page.
发表机构
- University of California, San Diego（加利福尼亚大学圣迭戈分校）
- Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。
