Conference Paper

Let's go public! taking a spoken dialog system to the real world.

Conference: INTERSPEECH 2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005
Source: DBLP


In this paper, we describe how a research spoken dialog system was made available to the general public. The Let's Go Public spoken dialog system provides bus schedule information to the Pittsburgh population during off-peak times. This paper describes the changes necessary to make the system usable for the general public and presents analysis of the calls and strategies we have used to ensure high performance.

Full-text preview

Available from:
  • Source
    • "Earlier, researchers from Philips implemented an automatic train timetable information desk for Germany [5] . More recently , Carnegie Mellon University provided Olympus [6], which has been used to build systems like the Let's Go! Bus Information System [7], leading to the biggest corpus of man-machine dialogs with real users publicly available today. Recent platforms for developing spoken dialogue systems include the Opendial toolkit [8] and the architecture developed by the University of Cambridge [9] for its startup VocalIQ. "

    Full-text · Conference Paper · Jan 2016
  • Source
    • "While this mechanism is smoothly handled in human communication, the same does not occur when humans talk to machines [1]. The dialogue in Table 1 from the Let's Go system [2] has several examples where repetitions could not be handled by the system and lead to miscommunication. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper addresses the problem of automatic detection of repeated turns in Spoken Dialogue Systems. Repetitions can be a symptom of problematic communication between users and systems. Such repetitions are often due to speech recognition errors, which in turn makes it hard to use speech recognition to detect repetitions. We present an approach to detect repetition using the phonetic distance to find the best alignment between turns in the same dialogue. The alignment score obtained is combined with different features to improve repetition detection. To evaluate the method proposed we compare several alignment techniques from edit distance to DTW-based distance, previously used in Spoken-Term detection tasks. We also compare two different methods to compute the phonetic distance: the first one using the phoneme sequence, and the second one using the distance between the phone posterior vectors. Two different datasets were used in this evaluation: a bus-schedule information system (in English) and a call routing system (in Swedish). The results show that approaches using phoneme distances over-perform approaches using Levenshtein distances between ASR outputs for repetition detection.
    Full-text · Conference Paper · Sep 2015
  • Source
    • "The context was the Noctívago system, an experimental agenda-based SDS in European Portuguese that provides schedule information about night buses in Lisbon. The first version of the system was adapted from Let's Go [7], a live system that gives bus schedule information for real users in Pittsburgh since 2005. Both telephone systems were based on the Olympus open-source architecture for SDSs [8], and used Ravenclaw [9], an agenda-based dialog manager. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes an approach to the use of lexical entrainment in Spoken Dialog Systems. This approach aims to increase the dialog success rate by adapting the lexical choices of the system to the user's lexical choices. If the system finds that the users lexical choice degrades the performance, it will try to establish a new conceptual pact, proposing other words that the user may adopt, in order to be more successful in task completion. The approach was implemented and tested in two different systems. Tests showed a relative dialog estimated error rate reduction of 10% and a relative reduction in the average number of turns per session of 6%.
    Full-text · Conference Paper · Oct 2013
Show more