Title :
To catch a chorus: using chroma-based representations for audio thumbnailing
Author :
Bartsch, Mark A. ; Wakefield, Gregory H.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
Abstract :
An important application for use with multimedia databases is a browsing aid, which allows a user to quickly and efficiently preview selections from either a database or from the results of a database query. Methods for facilitating browsing, though, are necessarily media dependent. We present one such method that produces short, representative samples (or "audio thumbnails") of selections of popular music. This method attempts to identify the chorus or refrain of a song by identifying repeated sections of the audio waveform. A reduced spectral representation of the selection based on a chroma transformation of the spectrum is used to find repeating patterns. This representation encodes harmonic relationships in a signal and thus is ideal for popular music, which is often characterized by prominent harmonic progressions. The method is evaluated over a sizable database of popular music and found to perform well, with most of the errors resulting from songs that do not meet our structural assumptions
Keywords :
audio signal processing; information retrieval; multimedia databases; music; pattern recognition; spectral analysis; audio thumbnail; browsing aid; chroma transformation; chroma-based representations; chromagram; harmonic progressions; multimedia databases; repeating patterns; retrieval systems; selection previews; song chorus; song refrain; Audio databases; Costs; Image databases; Marine vehicles; Multimedia databases; Multimedia systems; Multiple signal classification; Performance evaluation; Sampling methods; Speech;
Conference_Titel :
Applications of Signal Processing to Audio and Acoustics, 2001 IEEE Workshop on the
Conference_Location :
New Platz, NY
Print_ISBN :
0-7803-7126-7
DOI :
10.1109/ASPAA.2001.969531
