A Reranking Approach for Recognition and Classification of Speech Input in Conversational Dialogue Systems (bibtex)
by Morbini, Fabrizio, Audhkhasi, Kartik, Artstein, Ron, Van Segbroeck, Maarten, Sagae, Kenji, Georgiou, Panayiotis G., Traum, David and Narayanan, Shri
Abstract:
We address the challenge of interpreting spoken input in a conversational dialogue system with an approach that aims to exploit the close relationship between the tasks of speech recognition and language understanding through joint modeling of these two tasks. Instead of using a standard pipeline approach where the output of a speech recognizer is the input of a language understanding module, we merge multiple speech recognition and utterance classification hypotheses into one list to be processed by a joint reranking model. We obtain substantially improved performance in language understanding in experiments with thousands of user utterances collected from a deployed spoken dialogue system.⬚⬚⬚
Reference:
A Reranking Approach for Recognition and Classification of Speech Input in Conversational Dialogue Systems (Morbini, Fabrizio, Audhkhasi, Kartik, Artstein, Ron, Van Segbroeck, Maarten, Sagae, Kenji, Georgiou, Panayiotis G., Traum, David and Narayanan, Shri), In IEEE Workshop on Spoken Language Technology, 2012.
Bibtex Entry:
@inproceedings{morbini_reranking_2012,
	address = {Miami, Florida},
	title = {A {Reranking} {Approach} for {Recognition} and {Classification} of {Speech} {Input} in {Conversational} {Dialogue} {Systems}},
	url = {http://ict.usc.edu/pubs/A%20Reranking%20Approach%20for%20Recognition%20and%20Classification%20of%20Speech%20Input%20in%20Conversational%20Dialogue%20Systems.pdf},
	abstract = {We address the challenge of interpreting spoken input in a conversational dialogue system with an approach that aims to exploit the close relationship between the tasks of speech recognition and language understanding through joint modeling of these two tasks. Instead of using a standard pipeline approach where the output of a speech recognizer is the input of a language understanding module, we merge multiple speech recognition and utterance classification hypotheses into one list to be processed by a joint reranking model. We obtain substantially improved performance in language understanding in experiments with thousands of user utterances collected from a deployed spoken dialogue system.⬚⬚⬚},
	booktitle = {{IEEE} {Workshop} on {Spoken} {Language} {Technology}},
	author = {Morbini, Fabrizio and Audhkhasi, Kartik and Artstein, Ron and Van Segbroeck, Maarten and Sagae, Kenji and Georgiou, Panayiotis G. and Traum, David and Narayanan, Shri},
	month = dec,
	year = {2012},
	keywords = {Virtual Humans, UARC}
}
Powered by bibtexbrowser