Extracting semantically-coherent keyphrases from speech

Auteurs-es

  • Diana Inkpen Sch. of Info. Technology and Eng., University of Ottawa, 800 King Edward St., Ottawa, Ont. K1N6H5, Canada
  • Alain Désilets Institute for Information Technology, National Research Council, 1200 Montreal Rd., Ottawa, Ont. K1AOR6, Canada

Mots-clés :

Algorithms, Audio systems, Broadcasting, Error analysis, Semantics, Speech, Pointwise mutual information (PMI), Semantic coherence, Speech extractor systems, Word error rates (WER)

Résumé

A method for extracting keyphrase from spoken audio is discussed. The approach is based on the extractor system developed for text by Turney. The extractor uses a supervised learning approach to maximize the overlap between machine extracted and human extracted keyphrases. Each key word is detected with low similarity to its closest semantic neighbor, using an algorithm.

Fichiers supplémentaires

Publié-e

2004-09-01

Comment citer

1.
Inkpen D, Désilets A. Extracting semantically-coherent keyphrases from speech. Canadian Acoustics [Internet]. 1 sept. 2004 [cité 6 juill. 2026];32(3):130-1. Disponible à: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/1662

Numéro

Rubrique

Actes du congrès de la Semaine canadienne d'acoustique