Query by Singing/Humming System Based on Deep Learning

摘要

With the proliferation of digital music, efficient indexing and retrieval tools are required for searching the desired music in a large digital music database (DB). Traditional text-based information retrieval methods (titles, lyrics, singers, etc.) cannot meet people's needs now. Music information retrieval (MIR) has been a matter of interest. Therefore, how to retrieve the music information quickly and effectively becomes the focus of current research. In this paper, we propose a query-by-singing/humming system based on deep learning. The result shows our method is very promising in comparison with the published QbSH system based on monophonic database.