Continuous Speech Recognition Using Attention Shift Decoding with Soft Decision (bibtex)
by Kalinli, Ozlem and Narayanan, Shrikanth
Abstract:
We present an attention shift decoding (ASD) method inspired by human speech recognition. In contrast to the traditional auto- matic speech recognition (ASR) systems, ASD decodes speech inconsecutively using reliability criteria; the gaps (unreliable speech regions) are decoded with the evidence of islands (reli- able speech regions). On the BU Radio News Corpus, ASD pro- vides significant improvement (2.9% absolute) over the baseline ASR results when it is used with oracle island-gap informa- tion. 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.
Reference:
Continuous Speech Recognition Using Attention Shift Decoding with Soft Decision (Kalinli, Ozlem and Narayanan, Shrikanth), In Proceedings of Interspeech 2009, 2009.
Bibtex Entry:
@inproceedings{kalinli_continuous_2009,
	address = {Brighton, UK},
	title = {Continuous {Speech} {Recognition} {Using} {Attention} {Shift} {Decoding} with {Soft} {Decision}},
	url = {http://ict.usc.edu/pubs/Continuous%20Speech%20Recognition%20Using%20Attention%20Shift%20Decoding%20with%20Soft%20Decision.pdf},
	abstract = {We present an attention shift decoding (ASD) method inspired by human speech recognition. In contrast to the traditional auto- matic speech recognition (ASR) systems, ASD decodes speech inconsecutively using reliability criteria; the gaps (unreliable speech regions) are decoded with the evidence of islands (reli- able speech regions). On the BU Radio News Corpus, ASD pro- vides significant improvement (2.9\% absolute) over the baseline ASR results when it is used with oracle island-gap informa- tion. 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.},
	booktitle = {Proceedings of {Interspeech} 2009},
	author = {Kalinli, Ozlem and Narayanan, Shrikanth},
	month = oct,
	year = {2009}
}
Powered by bibtexbrowser