From rule-based to statistical grammars: Continuous improvement of large-scale spoken dialog systems

Statistical Spoken LanguageUnderstandinggrammars (SSLUs) are often used only at the top recognition contexts of modern large-scale spoken dialog systems. We propose to use SSLUs at every recognition context in a dialog system, effectively replacing conventional, manually written grammars. Furthermore, we present a methodology of continuous improvement in which data are collected at every recognition context over an entire dialog system. These data are then used to automatically generate updated context-specific SSLUs at regular intervals and, in so doing, continually improve system performance over time. We have found that SSLUs significantly and consistently outperform even the most carefully designed rule-based grammars in a wide range of contexts in a corpus of over two million utterances collected for a complex call-routing and troubleshooting dialog system.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: David Suendermann, Keelan Evanini, Jackson Liscombe, Phillip Hunter, Krishna Dayanidhi, Roberto Pieraccini
• Keywords: Dialog System, ICASSP 2009, Large-scale Spoken Dialog, Recognition Context, Signal Processing