Improving the performance of backpropagation-trained vowel classifiers
Gregory R. De Haan, Ömer Eğeci̇oğlu, Hisashi J. Wakita · The Journal of the Acoustical Society of America · 1988
Classification experiments using nine steady-state vowels were performed to compare artificial neural networks trained via backpropagation and K-nearest neighbor (KNN) classifiers. Normalized critical-band filterbank outputs served as input patterns in all experiments. Initial experiments used prototypical feedforward networks [R. Lippmann, IEEE ASSP Mag. 4(2), 4–22 (1987)], with fully interconnected adjacent layers of units. Once the critical number of hidden units [D. J. Burr, J. Acoust. Soc. Am. Suppl. 1 83, S46 (1988)] was established for a given experiment, the networks compared favorably to KNN. Significantly, while networks with two hidden layers did better than networks with one hidden layer for (binary) front-back vowel distinctions, they performed worse for (nine-class) vowel classification. It appears that backpropagation may be particularly powerful for binary classification [e.g., R. P. Gorman and T. J. Sejnowski, Neural Networks 1, 75–89 (1988)]. Experiments were run comparing prototypical networks with partitioned networks, where each hidden unit was connected to only one of the output units. Preliminary results indicate that these partitioned networks, which in effect do nine independent binary classifications in parallel, outperform the prototypical networks, suggesting that the critical number limit on performance can be overcome in a straightforward manner.