Handling Out-of-Grammar Commands in Mobile Speech Interaction Using Backoff Filler Models
Abstract
In command and control (C and C) speech interaction, users interact by speaking commands or asking questions typically specified in a context-free grammar (CFG). Unfortunately, users often produce out-of-grammar (OOG) commands, which can result in misunderstanding or nonunderstanding. We explore a simple approach to handling OOG commands that involves generating a back off grammar from any CFG using filler models, and utilizing that grammar for recognition whenever the CFG fails. Working within the memory footprint requirements of a mobile C and C product, applying the approach yielded a 35% relative reduction in semantic error rate for OOG commands. It also improved partial recognitions for enabling clarification dialogue.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2007
- Accession Number
- AD1170991
Entities
People
- David M. Chickering
- Sudeep Gandhe
- Tim Paek
- Yun C. Ju
Organizations
- University of Southern California