Abstract
This paper presents an audio classification and retrieval system using wavelets for extracting low-level acoustic features. The author performed multiple-level decomposition using discrete wavelet transform to extract acoustic features from audio recordings at different scales and times. The extracted features are then translated into a compact vector representation. Gaussian mixture models with expectation maximization algorithm are used to build models for audio classes and individual audio examples. The system is evaluated using three audio classification tasks: speech/music, male/female speech, and music genre. They also show how wavelets and Gaussian mixture models are used for class-based audio retrieval in two approaches: indexing using only wavelets versus indexing by Gaussian components. By evaluating the system through 10-fold cross-validation, the author shows the promising capability of wavelets and Gaussian mixture models for audio classification and retrieval. They also compare how parameters including frame size, wavelet level, Gaussian components, and sampling size affect performance in Gaussian models.
