@conference{cakir2015a,
author = "Emre Cakir and Toni Heittola and Heikki Huttunen and Tuomas Virtanen",
abstract = "In this paper, the use of multi label neural networks
are proposed for detection of temporally overlapping
sound events in realistic environments. Real-life sound recordings
typically have many overlapping sound events, making it
hard to recognize each event with the standard sound event
detection methods. Frame-wise spectral-domain features are
used as inputs to train a deep neural network for multi label
classification in this work. The model is evaluated with recordings
from realistic everyday environments and the obtained
overall accuracy is 63.8%. The method is compared against a
state-of-the-art method using non-negative matrix factorization
as a pre-processing stage and hidden Markov models as a
classifier. The proposed method improves the accuracy by 19%
percentage points overall.",
booktitle = "International Joint Conference on Neural Networks 2015 (IJCNN 2015)",
keywords = "Sound event detection;deep neural networks",
title = "{P}olyphonic sound event detection using multi label deep neural networks",
url = "https://www.cs.tut.fi/~cakir/publications/polyphonic-sound-event-ijcnn-2015.pdf",
year = "2015",
}