Polyphonic Sound Event Tracking using Linear Dynamical Systems

Overview

Description: This code performs sound event detection in complex acoustic environments. This version is trained with office sounds (16 event classes) from the DCASE 2013 Office Synthetic (OS) development set: http://c4dm.eecs.qmul.ac.uk/sceneseventschallenge/ . The output is a list of detected events per onset, offset, and event class.

If you use this code, please cite the following paper:
E. Benetos, G. Lafay, M. Lagrange, and M. D. Plumbley, "Polyphonic Sound Event Tracking using Linear Dynamical Systems", IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017.

Related publications

E. Benetos, G. Lafay, M. Lagrange, and M. D. Plumbley, “Polyphonic Sound Event Tracking using Linear Dynamical Systems,” IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017.: [More Details] [BIBT_EX]; @article{emmanouil2017a, author = {Emmanouil Benetos and Grégoire Lafay and Mathieu Lagrange and Mark D. Plumbley}, title = {Polyphonic Sound Event Tracking using Linear Dynamical Systems}, journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing}, note = {accepted}, year = {2017} }

Members

Manager: Emmanouil Benetos, Gregoire Lafay, Mark Plumbley, Mathieu Lagrange