Music-specific audio content analysis

Опубликовано 6 сентября 2016, 5:05

Advances in storage technology and audio compression have made possible the storage of large collections of music on personal computers and devices. In order to develop effective tools for browsing and searching these large collections, it is necessary to go beyond treating audio as a monolithic block of samples and create algorithms that in some ways understand the musical content. Although initial work in Music Information Retrieval (MIR) mainly used ideas and features from Speech Analysis, a recent trend has been to develop music-specific feature extraction and analysis algorithms. In this talk, I will present some of my work in this area. In addition, I will argue that in some ways music is a better choice for understanding perception than the more traditional areas of image, video and speech analysis.