Detail publikace

Gender Distinction Using Short Segments of Speech Signal

SIGMUND, M.

Originální název

Gender Distinction Using Short Segments of Speech Signal

Typ

článek v časopise - ostatní, Jost

Jazyk

angličtina

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.

Klíčová slova

Speech processing, gender recognition, short-time analysis

Autoři

SIGMUND, M.

Rok RIV

2008

Vydáno

31. 10. 2008

Nakladatel

Computer Science

Místo

Soul

ISSN

1738-7906

Periodikum

International Journal of Computer Science and Network Security

Ročník

8

Číslo

10

Stát

Korejská republika

Strany od

159

Strany do

162

Strany počet

4

BibTex

@article{BUT48854,
  author="Milan {Sigmund}",
  title="Gender Distinction Using Short Segments of Speech Signal",
  journal="International Journal of Computer Science and Network Security",
  year="2008",
  volume="8",
  number="10",
  pages="159--162",
  issn="1738-7906"
}