Non-negative matrix factorization of signals with overlapping events for event detection applications

In many event detection applications, training data may contain tags with multiple, simultaneous events. This is particularly likely when the definition of “event” is broad and includes events that can persist for an extended period of time. Decomposing a mixed signal into signals corresponding to individual events is non-trivial. In this paper, we propose a non-negative matrix factorization (NMF) method that generates independent dictionaries for different events from training data with overlapping events. The proposed method adds a mask matrix into the regularization term in conventional NMF approaches. This mask matrix captures known event labels in the training data, so that only related dictionary terms are updated during iteration. The effectiveness of the proposed approach is evaluated using both synthetic and real data.

[1]  J. Eggert,et al.  Sparse coding and NMF , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[2]  Heikki Huttunen,et al.  Polyphonic sound event detection using multi label deep neural networks , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[3]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[4]  J. Larsen,et al.  Wind Noise Reduction using Non-Negative Sparse Coding , 2007, 2007 IEEE Workshop on Machine Learning for Signal Processing.

[5]  Reishi Kondo,et al.  Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries , 2016, DCASE.

[6]  Heikki Huttunen,et al.  Recurrent neural networks for polyphonic sound event detection in real life recordings , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[7]  Reishi Kondo,et al.  Acoustic event detection based on non-negative matrix factorization with mixtures of local dictionaries and activation aggregation , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Onur Dikmen,et al.  Sound event detection using non-negative dictionaries learned from annotated overlapping events , 2013, 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[9]  Hyunsoo Kim,et al.  Sparse Non-negative Matrix Factorizations via Alternating Non-negativity-constrained Least Squares , 2006 .

[10]  Lida Xu,et al.  The internet of things: a survey , 2014, Information Systems Frontiers.

[11]  Michael Zeifman,et al.  Nonintrusive appliance load monitoring ( NIALM ) for energy control in residential buildings , 2011 .

[12]  Annamaria Mesaros,et al.  Sound Event Detection in Multisource Environments Using Source Separation , 2011 .

[13]  Renato D. C. Monteiro,et al.  Group Sparsity in Nonnegative Matrix Factorization , 2012, SDM.

[14]  Emmanuel Vincent,et al.  A General Flexible Framework for the Handling of Prior Information in Audio Source Separation , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[15]  Bart Vanrumste,et al.  An exemplar-based NMF approach to audio event detection , 2013, 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[16]  Tomer Toledo,et al.  In-vehicle data recorders for monitoring and feedback on drivers' behavior , 2008 .

[17]  David Wood,et al.  Acoustic Signal Processing for Anomaly Detection in Machine Room Environments: Demo Abstract , 2016, BuildSys@SenSys.

[18]  Francis Bach,et al.  Itakura-Saito nonnegative matrix factorization with group sparsity , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Antonio Iera,et al.  The Internet of Things: A survey , 2010, Comput. Networks.

[20]  Michael Zeifman,et al.  Nonintrusive appliance load monitoring: Review and outlook , 2011, IEEE Transactions on Consumer Electronics.

[21]  Guillaume Lemaitre,et al.  Real-Time Detection of Overlapping Sound Events with Non-Negative Matrix Factorization , 2013 .

[22]  C. D. Meyer,et al.  Initializations for the Nonnegative Matrix Factorization , 2006 .

[23]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[24]  Tuomas Virtanen,et al.  Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features , 2017, DCASE.