学习音乐循环片段中的正常模式
Learning Normal Patterns in Musical Loops
AI总结：
本文提出一种结合HTS-AT特征提取与Deep SVDD的无监督异常检测框架，通过潜在空间评分有效识别可变长音乐循环片段中的音频模式，克服了传统方法依赖手工特征和用户交互的局限。
摘要：
本文引入了一个无监督框架，通过异常检测技术检测音乐样本（循环片段）中的音频模式，以应对音乐信息检索（MIR）中的挑战。现有方法常受限于依赖手工特征、特定领域限制或依赖迭代用户交互。我们通过结合深度特征提取与无监督异常检测的架构来解决这些局限。该方法利用预训练的分层令词语义音频变换器（HTS-AT），结合特征融合机制（FFM），从可变长度的音频循环中生成表示。这些嵌入向量使用单类深度支持向量数据描述（Deep SVDD）进行处理，该模型通过将音频模式映射到紧凑的潜在超球体来学习规范音频模式。在精选的贝斯和吉他数据集上的评估，将标准和残差自编码器变体与孤立森林（IF）和主成分分析（PCA）等基线方法进行了比较。结果表明，我们的Deep SVDD模型，尤其是残差自编码器变体，提供了更好的异常分离效果，特别是对于较大的变体。本研究为处理多样化音频样本贡献了一个灵活、完全无监督的解决方案，克服了先前的结构和输入限制，同时通过基于距离的潜在空间评分实现了有效的模式识别。
英文摘要：
This paper introduces an unsupervised framework for detecting audio patterns in musical samples (loops) through anomaly detection techniques, addressing challenges in music information retrieval (MIR). Existing methods are often constrained by reliance on handcrafted features, domain-specific limitations, or dependence on iterative user interaction. We address these limitations through an architecture combining deep feature extraction with unsupervised anomaly detection. Our approach leverages a pre-trained Hierarchical Token-semantic Audio Transformer (HTS-AT), paired with a Feature Fusion Mechanism (FFM), to generate representations from variable-length audio loops. These embeddings are processed using one-class Deep Support Vector Data Description (Deep SVDD), which learns normative audio patterns by mapping them to a compact latent hypersphere. Evaluations on curated bass and guitar datasets compare standard and residual autoencoder variants against baselines like Isolation Forest (IF) and and principle component analysis (PCA) methods. Results show our Deep SVDD models, especially the residual autoencoder variant, deliver improved anomaly separation, particularly for larger variations. This research contributes a flexible, fully unsupervised solution for processing diverse audio samples, overcoming previous structural and input limitations while enabling effective pattern identification through distance-based latent space scoring.
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。
