Spoken Dialog Challenge 2010

作者: Alan W Black , Susanne Burger , Brian Langner , Gabriel Parent , Maxine Eskenazi

DOI: 10.1109/SLT.2010.5700894

关键词: Computer scienceSemantic interpretationDialog systemTask (project management)Natural language processingSpoken dialogImplementationArtificial intelligenceSpeech processingDialog box

摘要: This paper describes the 2010 Spoken Dialog Challenge, a multi-site challenge to help investigate different spoken dialog system and evaluation techniques. The aim of Challenge is bring together multiple implementations same task deploy them in uncontrolled real user conditions then make results available for common gives an overview teh itself task, presents “controlled task” part evaluation. also discusses infrastructure organizational issues encountered solutions that made this possible.

参考文章(4)
Maxine Eskenazi, Antoine Raux, Diane J. Litman, Hua Ai, Dan Bohus, Comparing Spoken Dialog Corpora Collected with Recruited Subjects versus Real Users annual meeting of the special interest group on discourse and dialogue. pp. 124- 131 ,(2007)
Maxine Eskénazi, Brian Langner, Antoine Raux, Alan W. Black, Dan Bohus, Doing Research on a Deployed Spoken Dialogue System: One Year of Let's Go! Experience conference of the international speech communication association. ,(2006)
Julie E. Boland, Marilyn A. Walker, Rebecca Passonneau, Quantitative and qualitative evaluation of Darpa Communicator spoken dialogue systems Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01. pp. 515- 522 ,(2001) , 10.3115/1073012.1073078
Gabriel Parent, Maxine Eskenazi, Toward better crowdsourced transcription: Transcription of a year of the Let's Go Bus Information System data spoken language technology workshop. pp. 312- 317 ,(2010) , 10.1109/SLT.2010.5700870