Mobile Information Access with Spoken Query Answering

Tom Brøndsted, Henrik Legind Larsen, Lars Bo Larsen, Børge Lindberg, Daniel Ortiz-Arroyo, Zheng-Hua Tan, Haitian Xu

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

626 Downloads (Pure)

Abstract

This paper addresses the problem of information and service accessibility in mobile devices with limited resources. A solution is developed and tested through a prototype that applies state-of-the-art Distributed Speech Recognition (DSR) and knowledge-based Information Retrieval (IR) processing for spoken query answering. For the DSR part, a configurable DSR system is implemented on the basis of the ETSI-DSR advanced front-end and the SPHINX IV recognizer. For the knowledge-based IR part, a distributed system solution is developed for fast retrieval of the most relevant documents, with a text window focused over the part which most likely contains an answer to the query. The two systems are integrated into a full spoken query answering system. The prototype can answer queries and questions within the chosen football (soccer) test domain, but the system has the flexibility for being ported to other domains.
Original languageEnglish
Title of host publicationProc. Workshop on Applied Spoken Language Interaction in Distributed Environments
Number of pages4
PublisherDenmark.
Publication date2006
ISBN (Print)8790834852
Publication statusPublished - 2006
EventASIDE 2005 - Aalborg
Duration: 10 Nov 200511 Nov 2005

Conference

ConferenceASIDE 2005
CityAalborg
Period10/11/200511/11/2005

Keywords

  • Distributed Speech Recognition, Information retrieval, Information Extraction

Fingerprint

Dive into the research topics of 'Mobile Information Access with Spoken Query Answering'. Together they form a unique fingerprint.

Cite this