Acoustic Event Classification using Low-Resolution Multi-label Non-negative Matrix Deconvolution

Vuegen L, Karsmakers P, Vanrumste B, Hamme HV. Acoustic Event Classification using Low-Resolution Multi-label Non-negative Matrix Deconvolution. J Audio Eng Soc. 2018;66(5):369-384. doi:10.17743/jaes.2018.0018

@article{Vuegen2018_19567,
  author = {Vuegen, Lode and Karsmakers, Peter and Vanrumste, Bart and Hamme, Hugo Van},
  title = {{Acoustic Event Classification using Low-Resolution Multi-label Non-negative Matrix Deconvolution}},
  journal = {Journal of the Audio Engineering Society},
  volume = {66},
  number = {5},
  pages = {369--384},
  year = {2018},
  month = may,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2018.0018},
  url = {https://doi.org/10.17743/jaes.2018.0018}
}

TY  - JOUR
TI  - Acoustic Event Classification using Low-Resolution Multi-label Non-negative Matrix Deconvolution
AU  - Vuegen, Lode
AU  - Karsmakers, Peter
AU  - Vanrumste, Bart
AU  - Hamme, Hugo Van
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 66
IS  - 5
SP  - 369
EP  - 384
PY  - 2018
DA  - 2018/05/06
DO  - 10.17743/jaes.2018.0018
UR  - https://doi.org/10.17743/jaes.2018.0018
PB  - Audio Engineering Society
LA  - en
AB  - With the increased proliferation of interconnected devices that have built-in microphones, acoustic event classification and monitoring becomes possible in a wide variety of applications, such as surveillance, healthcare, military, machine diagnostics, and wildlife tracking. The promise and success of these applications depends on robust sensing of acoustic events in the environment. Typically, sound event classes are defined by annotating training data, which is a laborious process. This work introduces an extended version of non-negative matrix deconvolution (NMD), called low-resolution multi-label non-negative matrix deconvolution (LRM-NMD), where both the observation data and the available labeling information are used during training. The proposed extension of NMD was successfully applied to the classification of acoustic events even in noisy conditions with overlapping events. Low-resolution, multi-labeling information simply indicates that the sound classes of the events take place over a longer period of time in the acoustic data without identifying beginning or endings of the individual events.
ER  -