Improved Word Confidence Estimation using Long Range Features
作者： Mari Ostendorf , David D. Palmer
DOI:
关键词: Artificial intelligence 、 Sequence 、 Word (computer architecture) 、 Speech recognition 、 Estimation 、 Information extraction 、 Named entity 、 Range (mathematics) 、 Computer science 、 Pattern recognition
摘要: This paper describes experiments in improving word confidence estimation using document- and task-level features of the hypothesized sequence from a recognizer. The improved estimates are shown to improve information extraction performance, specifically named entity (NE) recognition. detected names can then be used further multi-pass NE recognition framework.
isca-speech.org参考文章(10)
Man-Hung Siu, Fred Richardson, Herbert Gish, Improved estimation, evaluation and applications of confidence measures for speech recognition. conference of the international speech communication association. ,(1997)
Thomas Kemp, Thomas Schaaf, Estimating confidence using word lattices. conference of the international speech communication association. ,(1997)
G Evermann, PC Woodland, Posterior probability decoding, confidence estimation and system combination NIST: National Institute of Standards and Technology. ,(2000)
Peter McCullagh, John Ashworth Nelder, Generalized Linear Models ,(1983)
Richard A Olshen, Charles J Stone, Leo Breiman, Jerome H Friedman, Classification and regression trees ,(1983)
David D. Palmer, Mari Ostendorf, John D. Burger, Robust information extraction from automatically generated speech transcriptions Speech Communication. ,vol. 32, pp. 95- 109 ,(2000) , 10.1016/S0167-6393(00)00026-1
Manhung Siu, Herbert Gish, Evaluation of word confidence for speech recognition systems Computer Speech & Language. ,vol. 13, pp. 299- 319 ,(1999) , 10.1006/CSLA.1999.0126
L. Gillick, Y. Ito, J. Young, A probabilistic approach to confidence estimation and evaluation international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 879- 882 ,(1997) , 10.1109/ICASSP.1997.596076
M. Weintraub, F. Beaufays, Z. Rivlin, Y. Konig, A. Stolcke, Neural-network based measures of confidence for word recognition international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 887- 890 ,(1997) , 10.1109/ICASSP.1997.596078
J. Yamron, Liam Gillick, Mary Ann Newman, P. Zhan, Nikolaus Wegmann, L. Manganaro, F. Scattone, "Dragon systems" automatic transcription system for the new TDT corpus language resources and evaluation. pp. 337- 342 ,(1998)