Experiments with time delay networks and dynamic time warping for speaker independent isolated digits recognition

By L. Eon Bottou, F. Fogelman-Soulié, P. Blanchet, J. Liénard. 1989

We descrtbe in thls paper a speaker Independent. global word recognition task ustng time delay networks. We flrst descrtbe these networks as a way for leamlng feature extractors by constralned back-propagatlon. Such a tlme-delay network ls shown to be capable of deallng wlth a test task: French dlgtt recognttlon. The results are dlscussed and compared, on the same data sets, wlth those obtained wlth a classlcal time warping system. Both connectlonlst and classlcal systems achieved no more than 1% errors on the test set

Subfields: Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

Citations in the corpus

Character-level Convolutional Networks for Text Classification (2015, background): “In particular, time-delay networks used in the early days of deep learning research are essentially convolutional networks that model sequential data [1] [31].”
Optimization Methods for Large-Scale Machine Learning (2016, neutral): “…. . . 25 4.3 SG for General Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.4 Work Complexity for Large-Scale Learning . . . . . . . . . . . . . . . . . . . . . . . 33 4.5 Commentary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36”
End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks (2013, background): “It was extended to isolated word recognition [9].”