Detail publikace

Speaker Distinction Using Vowel Polygons: Experimental Study

Originální název

Speaker Distinction Using Vowel Polygons: Experimental Study

Anglický název

Speaker Distinction Using Vowel Polygons: Experimental Study

Jazyk

en

Originální abstrakt

This paper presents experimental study oriented on finding the most suitable polygon generated by Czech vowels for speaker recognition. For created speaker database containing 37 Czech native speakers, speaker variances have been observed by the length of vector created by two different centers of gravity for 16 different vowel polygons in 10 formant planes. The suitability is regarded by the dispersion coefficient of generated distance vectors and their minimal value. The most suitable vowel polygons have been set as EIOU25 tetragon and IOU34 vowel triangle reached the best results in both criteria. The dispersion of individual centers of gravity is much more suitable for speaker recognition generated by higher formants. Presented observations can be further used in the case of actual emotional state recognition or alcohol/drug detection.

Anglický abstrakt

This paper presents experimental study oriented on finding the most suitable polygon generated by Czech vowels for speaker recognition. For created speaker database containing 37 Czech native speakers, speaker variances have been observed by the length of vector created by two different centers of gravity for 16 different vowel polygons in 10 formant planes. The suitability is regarded by the dispersion coefficient of generated distance vectors and their minimal value. The most suitable vowel polygons have been set as EIOU25 tetragon and IOU34 vowel triangle reached the best results in both criteria. The dispersion of individual centers of gravity is much more suitable for speaker recognition generated by higher formants. Presented observations can be further used in the case of actual emotional state recognition or alcohol/drug detection.

BibTex


@inproceedings{BUT114247,
  author="Miroslav {Staněk} and Milan {Sigmund}",
  title="Speaker Distinction Using Vowel Polygons: Experimental Study",
  annote="This paper presents experimental study oriented
on finding the most suitable polygon generated by Czech vowels
for speaker recognition. For created speaker database containing
37 Czech native speakers, speaker variances have been observed
by the length of vector created by two different centers of gravity
for 16 different vowel polygons in 10 formant planes.
The suitability is regarded by the dispersion coefficient
of generated distance vectors and their minimal value. The most
suitable vowel polygons have been set as EIOU25 tetragon
and IOU34 vowel triangle reached the best results in both
criteria. The dispersion of individual centers of gravity is much
more suitable for speaker recognition generated by higher
formants. Presented observations can be further used in the case
of actual emotional state recognition or alcohol/drug detection.
",
  booktitle="Proceedings of 25th International Conference Radioelektronika 2015",
  chapter="114247",
  howpublished="print",
  year="2015",
  month="april",
  pages="125--128",
  type="conference paper"
}