Detail publikace

Gender Distinction Using Short Segments of Speech Signal

Originální název

Gender Distinction Using Short Segments of Speech Signal

Anglický název

Gender Distinction Using Short Segments of Speech Signal

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 vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. For text-independent analysis, the speech duration of 500 ms was sufficient to identify male/female speakers with the accuracy of more than 93%. Automatic estimation of speaker's gender by her/his voice is an important factor to realize high-quality dialogue systems.

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 vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. For text-independent analysis, the speech duration of 500 ms was sufficient to identify male/female speakers with the accuracy of more than 93%. Automatic estimation of speaker's gender by her/his voice is an important factor to realize high-quality dialogue systems.

BibTex


@article{BUT48854,
  author="Milan {Sigmund}",
  title="Gender Distinction Using Short Segments of Speech Signal",
  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 vowels. Two different simple identifiers based on selected mel-frequency cepstral coefficients were evaluated. For text-independent analysis, the speech duration of 500 ms was sufficient to identify male/female speakers with the accuracy of more than 93%. Automatic estimation of speaker's gender by her/his voice is an important factor to realize high-quality dialogue systems.",
  address="Computer Science",
  chapter="48854",
  institution="Computer Science",
  journal="International Journal of Computer Science and Network Security",
  number="10",
  volume="8",
  year="2008",
  month="october",
  pages="159--162",
  publisher="Computer Science",
  type="journal article - other"
}