Pitched Instrument Onset Detection Based on Auditory Spectra
2009 (English)In: Proceedings of ISMIR - International Conference on Music Information Retrieval, 2009, 105-110 p.Conference paper (Refereed)
In this paper, a novel method for onset detection of music signals using auditory spectra is proposed. The auditory spectrogram provides a time-frequency representation that employs a sound processing model resembling the human auditory system. Recent work on onset detection employs DFT-based features, such as the spectral flux and group delay function. The spectral flux and group delay are introduced in the auditory framework and an onset detection algorithm is proposed. Experiments are conducted on a dataset covering 11pitched instrument types, consisting of 1829 onsets in total. Results indicate the superiority of the auditory representations over the DFT-based ones, with the auditory spectral flux exhibiting an onset detection improvement by 2% in terms of F-measure when compared to the DFT-based feature.
Place, publisher, year, edition, pages
2009. 105-110 p.
Media and Communication Technology
IdentifiersURN: urn:nbn:se:kth:diva-193735ScopusID: 2-s2.0-84873668480OAI: oai:DiVA.org:kth-193735DiVA: diva2:1040445
10th International Society for Music Information Retrieval Conference, ISMIR 2009; Kobe; Japan; 26 October 2009 through 30 October 2009
QC 201610312016-10-272016-10-102016-11-14Bibliographically approved