TR2002-57

The MERL SpokenQuery Information Retrieval System: A System for Retrieving Pertinent Documents from a Spoken Query

    •  Wolf, P., Raj, B., "The MERL SpokenQuery Information Retrieval System: A System for Retrieving Pertinent Documents from a Spoken Query", IEEE International Conference on Multimedia and Expo (ICME), August 2002, vol. 2, pp. 317-320.
      BibTeX TR2002-57 PDF
      • @inproceedings{Wolf2002aug,
      • author = {Wolf, P. and Raj, B.},
      • title = {The MERL SpokenQuery Information Retrieval System: A System for Retrieving Pertinent Documents from a Spoken Query},
      • booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
      • year = 2002,
      • volume = 2,
      • pages = {317--320},
      • month = aug,
      • url = {https://www.merl.com/publications/TR2002-57}
      • }
  • Research Areas:

    Artificial Intelligence, Speech & Audio

Abstract:

This papers describes some key concepts developed and used in the design of a spoken-query based information retrieval system developed at the Mitsubishi Electric Research Labs (MERL). Innovations in the system include automatic inclusion of signature terms of documents in the recognizer vocabulary, the use of uncertainty vectors to represent spoken queries, and a method of indexing that accommodates the usage of uncertainty vectors. This paper describes these techniques and includes experimental results that demonstrate their effectiveness.

 

  • Related News & Events

    •  NEWS    ICME 2002: 3 publications by Chia Shen and others
      Date: August 26, 2002
      Where: IEEE International Conference on Multimedia and Expo (ICME)
      Brief
      • The papers "The MERL SpokenQuery Information Retrieval System: A System for Retrieving Pertinent Documents from a Spoken Query" by Wolf, P. and Raj, B., "PDH: A Human-Centric Interface for Image Libraries" by Moghaddam, B., Tian, Q., Lesh, N.B., Shen, C. and Huang, T.S. and "Constrained Video Object Segmentation by Color Masks and MPEG-7 Descriptors" by Porikli, F.M. and Wang, Y. were presented at the IEEE International Conference on Multimedia and Expo (ICME).
    •