Music identification via vocabulary tree with MFCC peaks

In this paper, a Vocabulary Tree based framework is proposed for music identification whose target is to recognize a fragment from a song database. The key to a high recognition precision within this framework is a novel feature, namely MFCC Peaks, which is a combination of MFCC and Spectral Peaks features. Our approach consists of three stages. We first build the Vocabulary Tree with 2 million MFCC Peaks features extracted from hundreds of music. Then each song in the database is quantified into some words by traveling from root down to a certain leaf. Given a query input, we apply the same quantization procedure to this fragment, score the archive according to the TF-IDF scheme and return the best matches. The experimental results demonstrate that our proposed feature has strong identifying and generalization ability. Other trials show that our approach scales well with the size of database. Further comparison also demonstrates that while our algorithm achieves approximately the same retrieval precision as other state-of-the-art methods, it cost less time and memory.