Comparative study of nonlinear time warping techniques in isolated word speech recognition systems

Waibel, A. ; Yegnanarayana, B. (1983) Comparative study of nonlinear time warping techniques in isolated word speech recognition systems IEEE Transactions on Acoustics, Speech & Signal Processing, 31 (6). pp. 1582-1586. ISSN 0096-3518

Full text not available from this repository.

Official URL: http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arn...

Related URL: http://dx.doi.org/10.1109/TASSP.1983.1164241

Abstract

In this paper, the effects of two major design choices on the performance of an isolated word speech recognition system are examined in detail. They are: 1) the choice of a warping algorithm among the Itakura asymmetric, the Sakoe and Chiba symmetric, and the Sakoe and Chiba asymmetric, and 2) the size of the warping window to reduce computation time. Two vocabularies were used: the digits (zero, one,..., nine) and a highly confusable subset of the alphabet (b, c, d, e, g, p, t, v, z). The Itakura asymmetric warping algorithm appears to be slightly better than the other two for the confusable vocabulary. We discuss the reasons why the performance of the algorithms is vocabulary dependent. Finally, for the data used in our experiments, a warping window of about 100 ms appears to be optimal.

Item Type:Article
Source:Copyright of this article belongs to IEEE.
ID Code:57783
Deposited On:29 Aug 2011 11:47
Last Modified:29 Aug 2011 11:47

Repository Staff Only: item control page