摘要
Recent efforts have been made on acoustic scene classification in the audio signal processing community. In contrast, few studies have been conducted on acoustic scene clustering, which is a newly emerging problem. Acoustic scene clustering aims at merging the audio recordings of the same class of acoustic scene into a single cluster without using prior information and training classifiers. In this study, we propose a method for acoustic scene clustering that jointly optimizes the procedures of feature learning and clustering iteration. In the proposed method, the learned feature is a deep embedding that is extracted from a deep convolutional neural network (CNN), while the clustering algorithm is the agglomerative hierarchical clustering (AHC). We formulate a unified loss function for integrating and optimizing these two procedures. Various features and methods are compared. The experimental results demonstrate that the proposed method outperforms other unsupervised methods in terms of the normalized mutual information and the clustering accuracy. In addition, the deep embedding outperforms many state-of-the-art features.
学科与关键词
- Sound Scene Clustering without Prior KnowledgeDawa, Yidemucao; Zhicheng, Zhao; Wu shour., SilamuCommunications in Computer and Information Science, Springer Berlin Heidelberg, 613-621, 2012.
- Speaker Clustering by Co-Optimizing Deep Representation Learning and Cluster EstimationLi, Yanxiong*; Wang, Wucheng; Liu, Mingle; Jiang, Zhongjie; He, QianhuaIEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23: 3377-3387.被引 7
- Deep mutual attention network for acoustic scene classificationXie, Wei; He, Qianhua*; Yu, Zitong; Li, YanxiongDigital Signal Processing: A Review Journal , 2022, 123: 103450.被引 7
