Cover image for Speaker-independent isolated digit recognition: multilayer perceptrons vs. dynamic time warping
Title:
Speaker-independent isolated digit recognition: multilayer perceptrons vs. dynamic time warping
General Note:
Neural networks. 3 : 453-465 ; 1990
Abstract:
Former experiments have shown the benefit of using specific multi-layer architectures,the so-called time dealy 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 away 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,onthe same data sets,with those obtained with a classical time warping system.
Subject Term:
Added Author:

Available:*

Library
Item Barcode
Call Number
Material Type
Item Category 1
Status
Searching...
30000001263577 MAK 3663 Open Access Book Article
Searching...

On Order