Enhancing commercial grammar-based applications using robust approaches to speech understanding
Matthieu Hébert · 2007
This paper presents a series of measurements of the accuracy of speech understanding when grammar-based or robust approaches are used. The robust approaches considered here are based on statistical language models (SLMs) with the interpretation being carried out by phrase-spotting or robust parsing methods. We propose a simple process to leverage existing grammars and logged utterances to upgrade grammar-based applications to become more robust to out-of-coverage inputs. All experiments herein are run on data collected from deployed directed dialog applications and show that SLM-based techniques outperform grammar-based ones without requiring any change in the application logic.