TDNN-Extracted features

Abstract: Time Delay Neural Network (TDNN) is a technique, derived from MLP, which performs a time invariant processing in its lowest layers. This time invariant processing may be extracted from the network, in order to code the speech for an other classifier such as Dynamic Time Warping (DTW). The resulting hybrid system shows improved performances, with respect to both techniques used in isolation. This paper describes this technique, gives results on a multi-speaker, isolated word recognition task, and discusses its advantages.

Xavier Driancourt and Léon Bottou: TDNN-Extracted features, Proceedings of Neuro Nimes 90, EC2, Nimes, France, 1990.

nimes-1990.djvu nimes-1990.pdf nimes-1990.ps.gz

@inproceedings{driancourt-bottou-90,
  author = {Driancourt, Xavier and Bottou, {L\'eon}},
  title = {{TDNN}-Extracted features},
  booktitle = {Proceedings of Neuro Nimes 90},
  publisher = {EC2},
  address = {Nimes, France},
  year = {1990},
  url = {http://leon.bottou.org/papers/driancourt-bottou-90},
}