arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.11706cs.SDcs.LGeess.AS
收藏

文本条件音乐扩散模型的广义多源推理

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

Sapienza University of Rome(罗马智慧大学);Ca' Foscari University of Venice(威尼斯大学);Queen Mary University of London(伦敦玛丽女王大学)

Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà

AI总结:

本文提出广义多源推理方法,将多源扩散模型推广至任意文本条件时域扩散模型,无需分离数据即可生成连贯音源与伴奏,并适配Dirac分离器,在Slakh2100和MTG-Jamendo上取得有竞争力的结果。

摘要:

多源扩散模型(MSDM)支持组合式音乐生成任务:生成一组连贯的音源、创建伴奏以及执行音源分离。尽管它们具有多功能性,但它们需要估计音源上的联合分布,这要求预先分离的音乐数据,而这种数据很少可用,并且在训练时固定音源的数量和类型。本文将MSDM推广到任意以文本嵌入为条件的时域扩散模型。这些模型不需要分离数据,因为它们是在混合音频上训练的,可以参数化任意数量的音源,并允许丰富的语义控制。我们提出了一种推理过程,能够实现音源和伴奏的连贯生成。此外,我们改编了MSDM的Dirac分离器以执行音源分离。我们在Slakh2100和MTG-Jamendo上训练的扩散模型进行了实验,展示了在宽松数据设置下具有竞争力的生成和分离结果。

英文摘要:

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the joint distribution over the sources, necessitating pre-separated musical data, which is rarely available, and fixing the number and type of sources at training time. This paper generalizes MSDM to arbitrary time-domain diffusion models conditioned on text embeddings. These models do not require separated data as they are trained on mixtures, can parameterize an arbitrary number of sources, and allow for rich semantic control. We propose an inference procedure enabling the coherent generation of sources and accompaniments. Additionally, we adapt the Dirac separator of MSDM to perform source separation. We experiment with diffusion models trained on Slakh2100 and MTG-Jamendo, showcasing competitive generation and separation results in a relaxed data setting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑