Automated directory assistance system - from theory to practice

Abstract The automated directory assistance system (ADAS) is traditionally formulated as an automatic speech recognition (ASR) problem. Recently, it has been formulated as a voice search problem, where a spoken utterance is firstly converted into text, which in turn is used to search for the listing. In this paper, we focus on the design and development of the utterance-to-listing component of ADAS. We show that many theoretical and practical issues need to be resolved when applying the basic idea of voice search to the development of ADAS. We share our experiences in addressing these issues, especially in pre-processing the listing database, generating a high performance LM, and developing efficient, accurate, and robust search algorithms. Field tests of our prototype system indicate that an 81% task completion rate can be achieved. Index Terms : speech recognition, directory assistance, voice search, TFIDF, spoken dialog system, vector space model 1. Introduction An automated directory assistance system (ADAS) [1] [2] [3] [5] [6] is a spoken dialog system that provides the caller with the phone number and/or address of the business or residential listing he/she requests. It is a very complicated system that involves automatic speech recognition (ASR), listing lookup, disambiguation, and dialog design. The core element of the ADAS is the utterance-to-listing (U2L) component that maps an utterance K