ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

A transient detection algorithm for audio using iterative analysis of STFT

Thoshkahna, B and Nsabimana, F and Ramakrishnan, K (2011) A transient detection algorithm for audio using iterative analysis of STFT. In: Proceedings of the 12th International Society for Music Information Retrieval Conference, October 24-28, 2011, Miami (Florida), USA.

[img] PDF
Inte_Soci_Mus_Inf_Ret_Con_203_2011.pdf - Published Version
Restricted to Registered users only

Download (564kB) | Request a copy
Official URL: http://publica.fraunhofer.de/documents/N-201582.ht...


We propose an iterative algorithm to detect transient segments in audio signals. Short time Fourier transform(STFT) is used to detect rapid local changes in the audio signal. The algorithm has two steps that iteratively - (a) calculate a function of the STFT and (b) build a transient signal. A dynamic thresholding scheme is used to locate the potential positions of transients in the signal. The iterative procedure ensures that genuine transients are built up while the localised spectral noise are suppressed by using an energy criterion. The extracted transient signal is later compared to a ground truth dataset. The algorithm performed well on two databases. On the EBU-SQAM database of monophonic sounds, the algorithm achieved an F-measure of 90% while on our database of polyphonic audio an F-measure of 91% was achieved. This technique is being used as a preprocessing step for a tempo analysis algorithm and a TSR (Transients + Sines + Residue) decomposition scheme.

Item Type: Conference Proceedings
Publisher: International Society for Music Information Retrieval
Additional Information: Copyright of this article belongs to International Society for Music Information Retrieval.
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 28 Mar 2013 12:11
Last Modified: 28 Mar 2013 12:11
URI: http://eprints.iisc.ac.in/id/eprint/46257

Actions (login required)

View Item View Item