Speech Understanding Based on Keyword Extraction and Relations Between Words

Abstract

In this paper, we propose a method for speech understanding using a corpus. First, the method extracts keywords from an N-best list of speech recognizer output. This process employs two measures: a confidence measure of speech recognizer output and an association probability between words. Next, the method uses dependencies between keywords in a corpus. Finally, it evaluates relations (tagged labels) of the dependencies. Our method obtained high accuracy as compared with a method with only the confidence measure of the speech understanding module. The results show the effectiveness of the proposed method.

Collaborative model of interaction and Unmanned Vehicle Systems' interface

“…Each kind of methods is mono-strategic or support a little set of possible strategies. Existing methods are interpretation based on keyword recognition [12], statistical methods based on heuristics [13], more pragmatics-based approach [14], etc. In this paper (section II-C), we present an interaction model which is coherent with each type of method.…”