Connected Word Recognition (CWR) systems are needed for many consumer applications. In such applications cost is a major factor. Several architectures for HMM based CWR are examined to provide an optimal cost effective configuration. Three architectures were examined: a simple LTR with no skips, LTR with skips (LTR-WS) and Multi-Path LTR. The LTR-WS and the MP-LTR were shown to be superior to the simple LTR. The MPLTR exhibited the best results with long strings.
Cite as: Vaich, T., Cohen, A. (2000) Multi-path, context dependent SC-HMM architectures for improved connected word recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 234-237, doi: 10.21437/ICSLP.2000-794
@inproceedings{vaich00_icslp,
author={Tzur Vaich and Arnon Cohen},
title={{Multi-path, context dependent SC-HMM architectures for improved connected word recognition}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 234-237},
doi={10.21437/ICSLP.2000-794}
}