New Approaches to Spoken Document Retrieval

@article{Wechsler2000NewAT,
  title={New Approaches to Spoken Document Retrieval},
  author={Martin Wechsler and Eugen Munteanu and Peter Sch{\"a}uble},
  journal={Information Retrieval},
  year={2000},
  volume={3},
  pages={173-188}
}
This paper presents four novel techniques for open-vocabulary spoken document retrieval: a method to detect slots that possibly contain a query feature; a method to estimate occurrence probabilities; a technique that we call collection-wide probability re-estimation and a weighting scheme which takes advantage of the fact that long query features are detected more reliably. These four techniques have been evaluated using the TREC-6 spoken document retrieval test collection to determine the… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Compared to the overall best runs submitted to TREC-6, we observed an increase in terms of mean reciprocal rank of 4.3% for SRT and 4.5% for LTT respectively.
  • The results show that our methods improve retrieval effectiveness by up to 63% in the case of highly corrupted data (PRT).

Citations

Publications citing this paper.
SHOWING 1-4 OF 4 CITATIONS

Grapheme-to-phoneme conversion based on high-order Markov chain for spoken term detection by text query

  • 2017 IEEE East-West Design & Test Symposium (EWDTS)
  • 2017
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Building Test Speech Dataset on Russian Language for Spoken Document Retrieval Task

  • 2018 IEEE East-West Design & Test Symposium (EWDTS)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Spoken document retrieval system based on phonemic transcribing

  • 2017 IEEE East-West Design & Test Symposium (EWDTS)
  • 2017
VIEW 2 EXCERPTS
CITES BACKGROUND