1. Content analysis for audio classification and segmentation. Lie Lu et al. propose a robust approach to classify and segment an audio stream. They use methods based on KNN and LSP-VQ to segment speech and non-speech part, and then divide the non-speech part to music, environment and silence. pdf
2. Content-based audio classification and retrieval by support vector machines. Guodong Guo and Stan Z Li use SVM with binary tree recognition strategy to tackle audio classification problem, and propose a new metric, called distance-from-boundary for audio retrieval. www
3. Classification of audio signals using SVM and RBFNN. P Dhanalakshmi et al. extract some acoustic features from audio and put them into a SVM and RBFNN to do classification jobs. []

赞微海报分享