Method and system of audio retrieval and source separation

摘要

A method and a system (20) of audio retrieval and source separation are described. The method comprises the steps of: receiving (10) a textual query; retrieving (11) a preliminary audio sample from an auxiliary audio database; retrieving (12) a target audio sample from a target audio database; and separating (13) the retrieved target audio sample into a plurality of audio source signals. The corresponding system (20) comprises an input unit (21), a storing unit (22) and a processing unit (23) to implement the method.