Handling out-of-grammar commands in mobile speech interaction using backoff filler models

Authors:
Tim Paek;Sudeep Gandhe;David Maxwell Chickering;Yun Cheng Ju
Affiliations:
Microsoft Research, One Microsoft Way, Redmond, WA;USC Institute for Creative Technologies, Marina del Rey, CA;Microsoft Research, One Microsoft Way, Redmond, WA;Microsoft Research, One Microsoft Way, Redmond, WA
Venue:
SLP '07 Proceedings of the Workshop on Grammar-Based Approaches to Spoken Language Processing
Year:
2007

Citing 5
Cited 1

Foundations of statistical natural language processing

Foundations of statistical natural language processing
Universal speech interfaces

interactions
Adaptive Dialog Based upon Multimodal Language Acquisition

ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Targeted help for spoken dialogue systems: intelligent feedback improves naive users' performance

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Improving command and control speech recognition on mobile devices: using predictive user models for language modeling

User Modeling and User-Adapted Interaction

Rapidly deploying grammar-based speech applications with active learning and back-off grammars

SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

In command and control (C&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 backoff 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&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.