Three Dimensions of Pitched Instrument Onset Detection

• Published in: IEEE transactions on audio, speech, and language processing Vol. 18; no. 6; pp. 1517 - 1527
• Main Authors: Holzapfel, A, Stylianou, Y, Gedik, A C, Bozkurt, B
• Format: Journal Article
• Language: English
• Published: Piscataway, NJ IEEE 01.08.2010; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Automatic music transcription; Computer Science; Datalogi; Delay; Detection, estimation, filtering, equalization, prediction; Detectors; Event detection; Exact sciences and technology; group delay; Information and Communication Technology; Information theory; Information, signal and communications theory; Informations- och kommunikationsteknik; Instruments; Miscellaneous; music information retrieval; onset detection; Performance evaluation; Phase detection; Robustness; Signal and communications theory; Signal processing; Signal processing algorithms; Signal, noise; Speech and Music Communication; Tal- och musikkommunikation; Telecommunications and information theory; Performance evaluation; Audio signal processing; Acoustic signal; Automatic transcription; Instrumentation; Information retrieval; Acoustic signal processing; Automatic music transcription; onset detection; Three dimensional model; Accuracy; Phase detector; Information combining; Information processing; Database; Data fusion; Musical sound; Pitch(acoustics); Signal detection; Group delay; music information retrieval; group delay
• ISSN: 1558-7916; 1558-7924; 1558-7924
• DOI: 10.1109/TASL.2009.2036298

In this paper, we suggest a novel group delay based method for the onset detection of pitched instruments. It is proposed to approach the problem of onset detection by examining three dimensions separately: phase (i.e., group delay), magnitude and pitch. The evaluation of the suggested onset detectors for phase, pitch and magnitude is performed using a new publicly available and fully onset annotated database of monophonic recordings which is balanced in terms of included instruments and onset samples per instrument, while it contains different performance styles. Results show that the accuracy of onset detection depends on the type of instruments as well as on the style of performance. Combining the information contained in the three dimensions by means of a fusion at decision level leads to an improvement of onset detection by about 8% in terms of F-measure, compared to the best single dimension.