Genetic Programming for Automatic Stress Detection in Spoken English

Created by W.Langdon from gp-bibliography.bib Revision:1.4496

  author =       "Huayang Xie and Mengjie Zhang and Peter Andreae",
  title =        "Genetic Programming for Automatic Stress Detection in
                 Spoken English",
  institution =  "Computer Science, Victoria University of Wellington",
  year =         "2006",
  number =       "CS-TR-06-4",
  address =      "New Zealand",
  keywords =     "genetic algorithms, genetic programming, Speech
                 recognition, stress detection, decision trees, support
                 vector machines",
  URL =          "",
  URL =          "",
  abstract =     "This paper describes an approach to the use of genetic
                 programming (GP) for the automatic detection of
                 rhythmic stress in spoken New Zealand English. A
                 linear-structured GP system uses speaker independent
                 prosodic features and vowel quality features as
                 terminals to classify each vowel segment as stressed or
                 unstressed. Error rate is used as the fitness function.
                 In addition to the standard four arithmetic operators,
                 this approach also uses several other arithmetic,
                 trigonometric, and conditional functions in the
                 function set. The approach is evaluated on 60 female
                 adult utterances with 703 vowels and a maximum accuracy
                 of 92.61per cent is achieved. The approach is compared
                 with decision trees (DT) and support vector machines
                 (SVM). The results suggest that, on our data set, GP
                 outperforms DT and SVM for stress detection, and GP has
                 stronger automatic feature selection capability than DT
                 and SVM.",

Genetic Programming entries for Huayang Jason Xie Mengjie Zhang Peter Andreae