Real-Time Audio Retrieval Method and Automatic Commercial Detecting System

Abstract

This study presents a robust audio retrieval method and discusses its control strategy. In the method, the retrieval target is divided into short segments, each segment is searched respectively and a retrieval window is used to maintain a list of segments that can be searched simultaneously. The method can quickly detect and locate known sound in real-time audio stream, multimedia archives or the Internet. It can maintain high performance even if large part of target is absent in the input stream. Its retrieval speed can be adjusted by the length of retrieval window and is independent on target length. Using the proposed method, an automatic commercial detecting system is developed, which is used to detect and locate advertisements from real-time TV or radio broadcast audio signal and estimate broadcast length of them. The recall rate and precision rate of the system are 100 and 99.7% respectively.