ML Anthology

Automatic Speaker Recognition: An Application of Machine Learning

Brett Squires, Claude Sammut
ICML 1995 pp. 515-521
doi:10.1016/B978-1-55860-377-6.50070-0 /icml/1995/squires1995icml-automatic/

Abstract

Speaker recognition is the identification of a speaker from features of his or her speech. This paper describes the use of decision tree induction techniques to induce classification rules that automatically identify speakers. In a population of 30 speakers, the method described has a recognition rate of 100% for both text dependent and text independent utterances. Training times scale linearly with the population size.

ICML Semantic Scholar

Cite

Text

Squires and Sammut. "Automatic Speaker Recognition: An Application of Machine Learning." International Conference on Machine Learning, 1995. doi:10.1016/B978-1-55860-377-6.50070-0

Markdown

[Squires and Sammut. "Automatic Speaker Recognition: An Application of Machine Learning." International Conference on Machine Learning, 1995.](https://mlanthology.org/icml/1995/squires1995icml-automatic/) doi:10.1016/B978-1-55860-377-6.50070-0

BibTeX

@inproceedings{squires1995icml-automatic,
  title     = {{Automatic Speaker Recognition: An Application of Machine Learning}},
  author    = {Squires, Brett and Sammut, Claude},
  booktitle = {International Conference on Machine Learning},
  year      = {1995},
  pages     = {515-521},
  doi       = {10.1016/B978-1-55860-377-6.50070-0},
  url       = {https://mlanthology.org/icml/1995/squires1995icml-automatic/}
}