We present an attention shift decoding (ASD) method inspired by human speech recognition. In contrast to the traditional automatic speech recognition (ASR) systems, ASD decodes speech inconsecutively using reliability criteria; the gaps (unreliable speech regions) are decoded with the evidence of islands (reliable speech regions). On the BU Radio News Corpus, ASD provides significant improvement (2.9% absolute) over the baseline ASR results when it is used with oracle island-gap information. At the core of the ASD method is the automatic island-gap detection. Here, we propose a new feature set for automatic island-gap detection which achieves 83.7% accuracy. To cope with the imperfect nature of the island-gap classification, we also propose a new ASD algorithm using soft decision. The ASD with soft decision provides 0.4% absolute (2.2% relative) improvement over the baseline ASR results when it is used with automatically detected islands and gaps.
Cite as: Kalinli, O., Narayanan, S.S. (2009) Continuous speech recognition using attention shift decoding with soft decision. Proc. Interspeech 2009, 1927-1930, doi: 10.21437/Interspeech.2009-557
@inproceedings{kalinli09_interspeech,
author={Ozlem Kalinli and Shrikanth S. Narayanan},
title={{Continuous speech recognition using attention shift decoding with soft decision}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={1927--1930},
doi={10.21437/Interspeech.2009-557}
}