Technical reports

Retrieving spoken documents: VMR Project experiments

K. Spärck Jones, G.J.F. Jones, J.T. Foote, S.J. Young

May 1995, 28 pages

Abstract

This paper describes initial work on an application for the retrieval of spoken documents in multimedia systems. Speech documents pose a particular problem for retrieval since the contents are unknown. The VMR project seeks to address this problem for a video mail application by combining state of the art speech recognition with established document retrieval technologies to provide an effective and efficient retrieval tool. Experiments with a small spoken message collection show that retrieval precision for the spoken file can reach 90% of that obtained when the same file is used, as a benchmark, in text transcription form.

Full text

PDF (3.0 MB)

BibTeX record

@TechReport{UCAM-CL-TR-366,
  author =	 {Sp{\"a}rck Jones, K. and Jones, G.J.F. and Foote, J.T. and
          	  Young, S.J.},
  title = 	 {{Retrieving spoken documents: VMR Project experiments}},
  year = 	 1995,
  month = 	 may,
  url = 	 {https://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-366.pdf},
  institution =  {University of Cambridge, Computer Laboratory},
  doi = 	 {10.48456/tr-366},
  number = 	 {UCAM-CL-TR-366}
}