用语音、音乐结构和声音嵌入,从个人歌单中自动找混音素材。
Zero-Shot Crate Digging: DJ Tool Retrieval Using Speech Activity, Music Structure And CLAP Embeddings
- 结合语音活动检测、音乐边界分析与CLAP模型进行零样本检索。
- 在真实音乐库上验证,能有效识别出适合现场混音的音频片段。
- 适合需要快速找采样或过渡段的电子音乐人和制作人使用。
在嘻哈、节奏蓝调、雷鬼、舞厅及几乎所有电子/舞曲风格中,DJ工具是一组精心挑选的音频文件,用于提升现场表演和创意混音。本文提出一种方法,从个人音乐收藏中发现这些DJ工具。利用开源的语音/音乐活动检测、音乐边界分析工具,以及对比语言-音频预训练(CLAP)模型实现零样本音频分类,构建了一个新型系统,可有效检索或重新发现适合现场演出或录音室使用的优质混音素材。
原文摘要 · Abstract (English)
In genres like Hip-Hop, RnB, Reggae, Dancehall and just about every Electronic/Dance/Club style, DJ tools are a special set of audio files curated to heighten the DJ's musical performance and creative mixing choices. In this work we demonstrate an approach to discovering DJ tools in personal music collections. Leveraging open-source libraries for speech/music activity, music boundary analysis and a Contrastive Language-Audio Pretraining (CLAP) model for zero-shot audio classification, we demonstrate a novel system designed to retrieve (or rediscover) compelling DJ tools for use live or in the studio.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。