A system for retrieving speech documents

ABSTRACT

An information retrieval model is presented for the retrieval of speech documents, i.e. audio recordings containing speech. The indexing vocabulary consists of indexing features that have the following characteristics. First, they are easy to recognize by speech recognition methods. Second, the number of different indexing features is small such that a reasonable amount of training data is sufficent to train the hidden Markov models that are used by the speech recognition process. Third, the retrieval method based on such indexing features achieves an acceptable retrieval effectiveness as shown by experiments on text collections. Fourth, these indexing features cannot only be identified in speech documents but also in text documents. From the last characteristic follows that speech documents and text documents can be retrieved simultaneously. Analogously, the queries may contain either speech or text. Thus, we have a simple multimedia retrieval model where two different medias are indexed coherently. We also describe a prototype retrieval system under development.

REFERENCES

• 1: Y. Chiaramella , J. Nie, A retrieval model based on an extended modal logic and its application to the RIME experimental approach, Proceedings of the 13th annual international ACM SIGIR conference on Research and development in information retrieval, p.25-43, September 05-07, 1990, Brussels, Belgium [doi>10.1145/96749.98007]
• 2: de Heer, T. (1974). Experiments with Syntactic Traces in Information Retrieval. Information Storage gj Retrieval, 10,133-144.
• 3: Fox, E. A. (1990). Virginia Disc One. Virginia Polytechnic Institute and State University, Department of Computer Science.
• 4: Edward A. Fox, Standards and the emergence of digital multimedia systems, Communications of the ACM, v.34 n.4, p.26-29, April 1991 [doi>10.1145/103085.103086]
• 5: Edward A. Fox , Matthew B. Koll, Practical enhanced Boolean retrieval: experiences with SMART and SIRE systems, Information Processing and Management: an International Journal, v.24 n.3, p.257-267, May 1988 [doi>10.1016/0306-4573(88)90093-3]
• 6: H. P. Frei , P. Schäuble, Determining the effectiveness of retrieval algorithms, Information Processing and Management: an International Journal, v.27 n.2-3, p.153-164, Feb./March 1991 [doi>10.1016/0306-4573(91)90046-O]
• 7: Norbert Fuhr, Models for retrieval with probabilistic indexing, Information Processing and Management: an International Journal, v.25 n.1, p.55-72, 1989 [doi>10.1016/0306-4573(89)90091-5]
• 8: N. Fuhr , C. Buckley, Probabilistic document indexing from relevance feedback data, Proceedings of the 13th annual international ACM SIGIR conference on Research and development in information retrieval, p.45-61, September 05-07, 1990, Brussels, Belgium [doi>10.1145/96749.98008]
• 9: Ladefoged, P. (1975). A Course in Phone~ics. Harcourt Brace Jovanovich, Inc., New York.
• 10: Kai-Fu Lee , Raj Reddy, Automatic Speech Recognition: The Development of the Sphinx Recognition System, Kluwer Academic Publishers, Norwell, MA, 1988
• 11: Lee, K. F. (September, 1989b). Hidden Markov Models: Past, Present, Future. In European Conference on Speech Communication and Technology, pp. 148- 155.
• 12: Linde, Y., Buzo, A., & Gray, R. M. (1980). An Algorithm for Vector Quantizer Design. IEEE Transactions on Communication, 28(1),84-95.
• 13: John E. Markel , A. H. Gray, Linear Prediction of Speech, Springer-Verlag New York, Inc., Secaucus, NJ, 1982
• 14: Carlo Meghini , Fausto Rabitti , Costantino Thanos, Conceptual Modeling of Multimedia Documents, Computer, v.24 n.10, p.23-30, October 1991 [doi>10.1109/2.97248]
• 15: A. Desai Narasimhalu , Stavros Christodoulakis, Multimedia Information Systems: The Unfolding of a Reality, Computer, v.24 n.10, p.6-8, October 1991 [doi>10.1109/2.97253]
• 16: Porter, M. F. (1980). An Algorithm for Suffix Stripping. Program, 14(3),130-137.
• 17: Rabiner, L. R. (1989). Tutorial on Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE, 77(2),257-286.
• 18: Robertson, S. E. (1977). The Probability Ranking Principle in IR. Journal of Documentation, 33(4),294- 304.
• 19: Rose, R. C., Chang, E. I., & Lippmann, R. (1991). Techniques for Information Retrieval from Voice Messages. In International Conference on Acoustics, Speech, and Signal Processing, pp. 317-320.
• 20: Gerard Salton , Christopher Buckley, Term-weighting approaches in automatic text retrieval, Information Processing and Management: an International Journal, v.24 n.5, p.513-523, 1988 [doi>10.1016/0306-4573(88)90021-0]
• 21: Salton, G., & Buckley, C. (1990). Improving Retrieval Performance by Relevance Feedback. Journal of the ASIS, 41(4),288-297.
• 22: T.M.T Sembok , C.J. van Rijsbergen, SILOL: a simple logical-linguistic document retrieval system, Information Processing and Management: an International Journal, v.26 n.1, p.111-134, 1990 [doi>10.1016/0306-4573(90)90012-Q]
• 23: Shore, J. (1988). Interactive Signal Processing with UNIX. Speech Technology, 4(2),70-79.
• 24: Teufel, B. (1989). Informationsspuren zum numerischen und graphischen Vergleich yon reduzierten natiirlichsprachlichen Texten. PhD thesis, Swiss Federal Institute of Technology. VdF-Verlag, Ziirich.
• 25: H. Turtle , W. B. Croft, Inference networks for document retrieval, Proceedings of the 13th annual international ACM SIGIR conference on Research and development in information retrieval, p.1-24, September 05-07, 1990, Brussels, Belgium [doi>10.1145/96749.98006]
• 26: C. J. Van Rijsbergen, Information Retrieval, Butterworth-Heinemann, Newton, MA, 1979
• 27: Wilcox, L. D., & Bush, M. A. (1991). HMM-Based Wordspotting for Voice Editing and Indexing. In European Conference on Speech Communication and Technology, pp. 25-28.
• 28: Willet, P. (1979). Document Retrieval Experiments Using Indexing Vocabularies of Varying Size. II Hashing, Truncation, Digram and Trigram Encoding of Indexing Terms. Journal of Documentation, 35(4),296-305.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Indexing methods; Linguistic processing

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Speech recognition and synthesis

  J. Computer Applications
  J.5 ARTS AND HUMANITIES
      Subjects: Linguistics

General Terms:
Algorithms, Languages