arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.01740cs.SDcs.AIeess.AS
收藏

基于双模态语义相似性的弱监督音频分离

Weakly-supervised Audio Separation via Bi-modal Semantic Similarity

The University of Texas at Austin(得克萨斯大学奥斯汀分校);Microsoft Corporation(微软公司)

Tanvir Mahmud, Saeed Amizadeh, Kazuhito Koishida, Diana Marculescu

AI总结:

本文提出一种基于 CLAP 双模态语义相似性的弱监督音频分离框架,利用语言模态信号辅助音频单源分离,在无监督场景下 SDR 提升 71%,并可将监督学习性能进一步提升 17%。

摘要:

在多源音频混合中进行条件声音分离,且在训练期间无法获得单源声音数据,是一个长期存在的挑战。现有的基于“混合-分离”的方法由于在训练过程中缺乏针对单源分离情况的监督信号,在面对多源训练混合时性能显著下降。然而,在语言条件音频分离的情况下,我们确实可以在训练数据中获得每个音频混合对应的文本描述,这些文本描述可以视为音频样本在语言模态中的(粗略)表示。为此,在本文中,我们提出了一个通用的双模态分离框架,该框架能够增强现有的无监督框架,利用条件模态(即语言)中易于分离的对应信号,在目标模态(即音频)中分离单源信号,而无需在训练期间获得目标模态中的单源样本。我们通过实验证明,如果我们能够获得两种模态之间的预训练联合嵌入模型(即 CLAP),这一目标是完全可以实现的。此外,我们提出将我们的框架融入两个基本场景中以提升分离性能。第一,我们表明,所提出的方法通过减少训练样本与测试样本之间的分布偏移,显著提高了纯无监督基线的性能。特别是,我们表明我们的框架在信号失真比(SDR)方面相比基线可实现 71% 的提升,达到监督学习性能的 97.5%。第二,我们表明,如果用我们提出的弱监督框架对监督学习本身进行增强,可以将其性能进一步提升 17%,从而构建出一个强大的半监督音频分离框架。

英文摘要:

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop with multi-source training mixtures due to the lack of supervision signal for single source separation cases during training. However, in the case of language-conditional audio separation, we do have access to corresponding text descriptions for each audio mixture in our training data, which can be seen as (rough) representations of the audio samples in the language modality. To this end, in this paper, we propose a generic bi-modal separation framework which can enhance the existing unsupervised frameworks to separate single-source signals in a target modality (i.e., audio) using the easily separable corresponding signals in the conditioning modality (i.e., language), without having access to single-source samples in the target modality during training. We empirically show that this is well within reach if we have access to a pretrained joint embedding model between the two modalities (i.e., CLAP). Furthermore, we propose to incorporate our framework into two fundamental scenarios to enhance separation performance. First, we show that our proposed methodology significantly improves the performance of purely unsupervised baselines by reducing the distribution shift between training and test samples. In particular, we show that our framework can achieve 71% boost in terms of Signal-to-Distortion Ratio (SDR) over the baseline, reaching 97.5% of the supervised learning performance. Second, we show that we can further improve the performance of the supervised learning itself by 17% if we augment it by our proposed weakly-supervised framework, that enables a powerful semi-supervised framework for audio separation.

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。

↑