DocumentCode :
3391051
Title :
Multifeature audio segmentation for browsing and annotation
Author :
Tzanetakis, George ; Cook, Perry
Author_Institution :
Dept. of Comput. Sci., Princeton Univ., NJ, USA
fYear :
1999
fDate :
1999
Firstpage :
103
Lastpage :
106
Abstract :
Indexing and content-based retrieval are necessary to handle the large amounts of audio and multimedia data that is becoming available on the Web and elsewhere. Since manual indexing using existing audio editors is extremely time consuming a number of automatic content analysis systems have been proposed. Most of these systems rely on speech recognition techniques to create text indices. On the other hand, very few systems have been proposed for automatic indexing of music and general audio. Typically these systems rely on classification and similarity-retrieval techniques and work in restricted audio domains. A somewhat different, more general approach for fast indexing of arbitrary audio data is the use of segmentation based on multiple temporal features combined with automatic or semi-automatic annotation. In this paper, a general methodology for audio segmentation is proposed. A number of experiments were performed to evaluate the proposed methodology and compare different segmentation schemes. Finally, a prototype audio browsing and annotation tool based on segmentation combined with existing classification techniques was implemented
Keywords :
audio signal processing; content-based retrieval; database indexing; feature extraction; multimedia databases; online front-ends; signal classification; audio browsing/annotation tool; audio data; automatic annotation; automatic content analysis systems; automatic indexing; classification techniques; content-based retrieval; experiments; multifeature audio segmentation; multimedia data; multiple temporal features; similarity-retrieval techniques; speech recognition; text indices; Computer science; Content based retrieval; Humans; Image edge detection; Image segmentation; Indexing; Information retrieval; Prototypes; Sections; Speech;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 1999 IEEE Workshop on
Conference_Location :
New Paltz, NY
Print_ISBN :
0-7803-5612-8
Type :
conf
DOI :
10.1109/ASPAA.1999.810860
Filename :
810860
Link To Document :
بازگشت