Feature selection is applied to identify relevant and complementary features from a given high-dimensional feature set. In general, existing filter-based approaches operate on single (scalar) feature components and ignore the relationships among components of multidimensional features. As a result, generated feature subsets lack in interpretability and hardly provide insights into the underlying data. We propose an unsupervised, filter-based feature selection approach that preserves the natural assignment of feature components to semantically meaningful features. Experiments on different tasks in the audio domain show that the proposed approach outperforms well-established feature selection methods in terms of retrieval performance and runtime. Results achieved on different audio datasets for the same retrieval task indicate that the proposed method is more robust in selecting consistent feature sets across different datasets than compared approaches.

Top