A Speech-Based Human-Computer Interaction System for Automating Directory Assistance Services

• Published in: International journal of speech technology 2003-04, Vol.6 (2), p.145-159
• Main Authors: Georgila, K, Sgarbas, K, Tsopanoglou, A, Fakotakis, N, Kokkinakis, G
• Format: Article
• Language: English
• ISSN: 1381-2416
• DOI: 10.1023/A:1022338631326

The automation of Directory Assistance Services (DAS) through speech is one of the most difficult & demanding applications of human-computer interaction because it deals with very large vocabulary recognition issues. In this paper, we present a spoken dialogue system for automating DAS. Taking into account the major difficulties of this endeavor, a stepwise approach was adopted. In particular, two prototypes D1.1 (basic approach) & D1.2 (improved version) were developed successively. The results of D1.1 evaluation were used to refine D1.1 & gradually led to D1.2 that was also improved using a feedback approach. Furthermore, the system was extended & optimized so that it can be utilized in real-world conditions. We describe the general architecture & the three stages of the system's development in detail. Evaluation results concerning both the speech recognizer's accuracy & the overall system's performance are provided for all prototypes. Finally, we focus on techniques that handle large vocabulary recognition issues. The use of Directed Acyclic Word Graphs (DAWGs) & context-dependent phonological rules resulted in search space reduction & therefore in faster response & improved accuracy. 12 Tables, 4 Figures, 35 References. Adapted from the source document