Understanding speech in interactive narratives with crowd sourced data
Author(s)Orkin, Jeffrey David; Roy, Deb K.
MetadataShow full item record
Speech recognition failures and limited vocabulary coverage pose challenges for speech interactions with characters in games. We describe an end-to-end system for automating characters from a large corpus of recorded human game logs, and demonstrate that inferring utterance meaning through a combination of plan recognition and surface texts similarity compensates for recognition and understanding failures significantly better than relying on surface similarity alone.
DepartmentMassachusetts Institute of Technology. Media Laboratory; Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Proceedings of the Eighth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
Association for the Advancement of Artificial Intelligence (AAAI)
Orkin, Jeff and Deb K. Roy. "Understanding speech in interactive narratives with crowd sourced data." in Eighth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. October 8-12, 2012, Stanford University, Palo Alto, California. AAAI.
Author's final manuscript