Detail publikace

Automatic Gender Distinction by Voice

Originální název

Automatic Gender Distinction by Voice

Anglický název

Automatic Gender Distinction by Voice

Jazyk

en

Originální abstrakt

This paper presents and discusses an approach to automatic gender distinction in a short segment of normally spoken continuous speech. In order to see which phonemes are effective for gender recognition, we analyzed individual all Czech vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. Using vowel phonemes, we achieved in short-time analysis (20 msec) a gender identification accuracy of more than 90%.

Anglický abstrakt

This paper presents and discusses an approach to automatic gender distinction in a short segment of normally spoken continuous speech. In order to see which phonemes are effective for gender recognition, we analyzed individual all Czech vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. Using vowel phonemes, we achieved in short-time analysis (20 msec) a gender identification accuracy of more than 90%.

Dokumenty

BibTex


@misc{BUT60319,
  author="Milan {Sigmund} and Tomáš {Dostál}",
  title="Automatic Gender Distinction by Voice",
  annote="This paper presents and discusses an approach to automatic gender distinction in a short segment of normally spoken continuous speech. In order to see which phonemes are effective for gender recognition, we analyzed individual all Czech vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. Using vowel phonemes, we achieved in short-time analysis (20 msec) a gender identification accuracy of more than 90%.",
  address="M.H.Hamza",
  booktitle="Abstracts of IASTED International Conference on Artificial Intelligence and Applications – AIA 2005",
  chapter="60319",
  institution="M.H.Hamza",
  year="2005",
  month="february",
  pages="1",
  publisher="M.H.Hamza",
  type="abstract"
}