Rapid Development of Spoken Language Understanding Grammars

To facilitate the development of spoken dialog systems and speech enabled applications, we introduce SGStudio (Semantic Grammar Studio), a grammar authoring tool that enables regular software developers with little speech/linguistic background to rapidly create quality semantic grammars for automatic speech recognition (ASR) and spoken language understanding (SLU). We focus on the underlying technology of SGStudio, including knowledge assisted example-based grammar learning, grammar controls and configurable grammar structures. While the focus of SGStudio is to increase productivity, experimental results show that it also improves the quality of the grammars being developed. Key words: Automatic grammar generation, context free grammars (CFGs), example-based grammar learning, grammar controls, hidden Markov models (HMMs), n-gram model, automatic speech recognition (ASR), spoken language understanding