Sentence Structure for Dialog Act Recognition in Czech

This paper deals with automatic dialog acts (DAs) recognition in Czech based on sentence structure. We consider the following DAs: statements, orders, yes/no questions and other questions. In our previous works, we have proposed, implemented and evaluated new approaches to automatic DAs recognition based on sentence structure and prosody. The word sequences were manually transcribed. The main goal of this paper is to evaluate the performances of our approaches when these word sequences are unknown and estimated from a speech recognizer. Our system is tested on a Czech corpus that simulates a task of train tickets reservation. When manual transcription is used, classification accuracy without and with sentence structure models is 91 %, 94 % and 95 %. The recognition accuracy reaches 96 % with prosodic combination. When word sequences are estimated from a speech recognizer, the classification score is 88 % without and 91 % and 92 % with sentence structure models. The combination with prosody gives 93 % of accuracy.