No abstract

Integrating intelligent components into the speech interface ……… 5-3 The flow control of dialogues with a hybrid strategy ……………… 5-4 Overview of the corpus generation procedures …………………….. 5-5 Dialogue personalization architecture ……………………………… 6-1 Questionnaire items ……………………………………………….. X D-1 An example of product taxonomy …………………………………. D-2 Decision-tree based e-catalogue …………………………………… D-3 Speech recognition for application-directed dialogue ……………… D-4 An example grammar in JSGF ……………………………………..

Abstract. Corpus-based stochastic language models have achieved significant success in speech recognition, but construction of a corpus pertaining to a specific application is a difficult task. This paper introduces a Case-Based Reasoning system to generate natural language corpora. In comparison to traditional natural language generation approaches, this system overcomes the inflexibility of template-based methods while avoiding the linguistic sophistication of rule-based packages. The evaluation of the system indicates our approach is effective in generating users' specifications or queries as 98% of the generated sentences are grammatically correct. The study result also shows that the language model derived from the generated corpus can significantly outperform a general language model or a dictation grammar.

Designing a dialogue strategy for speech-enabled mobile commerce is a significant challenge due to the context. This paper introduces a hybrid dialogue strategy to overcome the inflexibility of application-directed interactions while avoiding the significant recognition difficulty of a full mixed-initiative style. The system uses N-Gram grammars to govern the recognition at the request segment of a dialogue, and employs an application-directed strategy at the clarification discourse segment. The paper also details generating a corpus for the N-Gram grammar through a Case-Based Reasoning approach, and constructing application-directed dialogues with decision trees. Our preliminary testing indicates the strategy is a feasible and effective solution for voice-enabling mobile commerce applications.