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.
Highlights
Rapid development of multimedia and network technology has resulted in large and ever-increasing stores of multimedia data
Audio, as an important media, has been paid more and more attentions. It is a kind of useful audio retrieval to search quickly through a long audio or video stream to detect and locate a known target audio signal
Control of retrieval response time Lag (RRTL): In real-time audio retrieval, when the reference template is found in the input stream, some action would be triggered, such as recording the TV or radio broadcast signal containing the reference template into multimedia files for late verification in commercial detecting system
Summary
Rapid development of multimedia and network technology has resulted in large and ever-increasing stores of multimedia data. Control of retrieval response time Lag (RRTL): In real-time audio retrieval, when the reference template is found in the input stream, some action would be triggered, such as recording the TV or radio broadcast signal containing the reference template into multimedia files for late verification in commercial detecting system. So as to search as many targets as possible; (2) given the number of reference templates to search, confirm the maximum value of retrieval window, M max , in order to obtain the best recall rate and precision rate. Both of the above aspects are about making the best use of system computing resource under a reliable load limit.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
