@inproceedings {Moritz1718_2016,
	year = {2016},
	author = {Moritz, Niko and Schröder, Jens and Goetze, Stefan and Anemüller, Jörn and Kollmeier, Birger},
	title = {Acoustic Scene Classification using Time-Delay Neural Networks and Amplitude Modulation Filter Bank Features},
	booktitle = {Detection and Classification of Acoustic Scenes and Events},
	abstract = {This  paper  presents  a  system  for  acoustic  scene  classification  (SC)  that  is  applied  to  data  of  the  SC  task  of  the  DCASE’16  challenge (Task 1). The proposed method is based on extracting acoustic features that employ a relatively long temporal context, i.e.,  amplitude  modulation  filer  bank  (AMFB)  features,  prior  to  detection  of  acoustic  scenes  using a neural network (NN) based classification  approach.  Recurrent  neural  networks  (RNN)  are  well  suited  to  model  long-term  acoustic  dependencies  that  are  known  to  encode  important  information  for  SC  tasks.  However,  RNNs require a relatively large amount of training data in comparison  to  feed-forward  deep  neural  networks  (DNNs).  Hence,  the  time-delay  neural  network  (TDNN)  approach  is  used  in  the  present  work  that  enables  analysis  of  long  contextual  information  similar  to  RNNs  but  with  training  efforts  comparable  to conventional DNNs. The proposed SC system attains a recognition accuracy of 76.5 %, which is 4.0 % higher compared to the DCASE’16 baseline system. }
}