Specialized Language Models using Dialogue Predictions

TL;DR

This paper demonstrates that dialogue-dependent language models tailored to specific system questions significantly improve speech recognition and understanding in spoken dialogue systems, outperforming generic models and other enhancement methods.

Contribution

It introduces dialogue-specific language models for each question type, showing their effectiveness over single models and other techniques in a railway timetable access system.

Findings

Dialogue-dependent models improve recognition accuracy.

Performance gains are consistent across different methods.

Models outperform baseline and other enhancement techniques.

Abstract

This paper analyses language modeling in spoken dialogue systems for accessing a database. The use of several language models obtained by exploiting dialogue predictions gives better results than the use of a single model for the whole dialogue interaction. For this reason several models have been created, each one for a specific system question, such as the request or the confirmation of a parameter. The use of dialogue-dependent language models increases the performance both at the recognition and at the understanding level, especially on answers to system requests. Moreover other methods to increase performance, like automatic clustering of vocabulary words or the use of better acoustic models during recognition, does not affect the improvements given by dialogue-dependent language models. The system used in our experiments is Dialogos, the Italian spoken dialogue system used for accessing railway timetable information over the telephone. The experiments were carried out on a large corpus of dialogues collected using Dialogos.