===== Speaker independent isolated digit recognition: Multilayer perceptron vs Dynamic Time Warping =====

//Abstract//: Former experiments have shown the benefit of using specific multi-layer architectures, the so-called
time delay neural networks, for phoneme recognition (Waibel, Hanazawa, Hinton, Shikano, & Lang, 1988).
Similar experiments on a speaker-independent task were also performed on a small set of minimal pairs (Bottou,
1988). In this paper we focus on a speaker-independent, global word recognition task with time delay networks.
We first describe these networks as a way for learning feature extractors by constrained back-propagation. Such
a time-delay network is shown to be capable of dealing with a near real-sizedproblem: French digit recognition.
The results are discussed and compared, on the same data sets, with those obtained with a classical time warping
system.

<box 99% orange>
Léon Bottou, Françoise Fogelman Soulié, Pascal Blanchet and Jean Sylvain Lienard:  **Speaker independent isolated digit recognition: Multilayer perceptron vs Dynamic Time Warping**,  //Neural Networks//, 3:453-465, 1990.

[[http://leon.bottou.org/publications/djvu/nnj-1990.djvu|nnj-1990.djvu]]
[[http://leon.bottou.org/publications/pdf/nnj-1990.pdf|nnj-1990.pdf]]
[[http://leon.bottou.org/publications/psgz/nnj-1990.ps.gz|nnj-1990.ps.gz]]
</box>

  @article{bottou-90,
    author = {Bottou, {L\'eon} and Fogelman Souli\'e, Fran\c{c}oise and Blanchet, Pascal and Lienard, {Jean Sylvain}},
    title = {Speaker independent isolated digit recognition: Multilayer perceptron vs Dynamic Time Warping},
    journal = {Neural Networks},
    year = {1990},
    volume = {3},
    pages = {453-465},
    url = {http://leon.bottou.org/papers/bottou-90},
  }