Publication detail

Speaker Dependent Coefficients for Speaker Recognition

ORSÁG, F.

Original Title

Speaker Dependent Coefficients for Speaker Recognition

English Title

Speaker Dependent Coefficients for Speaker Recognition

Type

journal article - other

Language

en

Original Abstract

This work aims at speaker recognition based upon a new set of features. Feature extraction is a crucial phase of the recognition process and a proper feature set dramatically influences the speaker recognition. Many well-known features are not suitable for the speaker recognition as those merge the specifics of the individual voices. Therefore, we need features accentuating the individual differences of our voices to be able to recognise speakers reliably. This work introduces new, speaker dependent features called Speaker Dependent Frequency Cepstrum Coefficients (SDFCC), created for the speaker recognition purposes only. Experimental results show their performance in comparison to the well-known features. According to the test results, the SDFCC are, for the speaker recognition, very useful and promising.

English abstract

This work aims at speaker recognition based upon a new set of features. Feature extraction is a crucial phase of the recognition process and a proper feature set dramatically influences the speaker recognition. Many well-known features are not suitable for the speaker recognition as those merge the specifics of the individual voices. Therefore, we need features accentuating the individual differences of our voices to be able to recognise speakers reliably. This work introduces new, speaker dependent features called Speaker Dependent Frequency Cepstrum Coefficients (SDFCC), created for the speaker recognition purposes only. Experimental results show their performance in comparison to the well-known features. According to the test results, the SDFCC are, for the speaker recognition, very useful and promising.

Keywords

speaker, recognition, verification, identification, features

RIV year

2010

Released

05.02.2010

Publisher

NEUVEDEN

Location

NEUVEDEN

ISBN

1738-9976

Periodical

International Journal of Security and Its Applications

Year of study

2010

Number

1

State

KR

Pages from

31

Pages to

47

Pages count

17

Documents

BibTex


@article{BUT50801,
  author="Filip {Orság}",
  title="Speaker Dependent Coefficients for Speaker Recognition",
  annote="This work aims at speaker recognition based upon a new set of features. Feature
extraction is a crucial phase of the recognition process and a proper feature set
dramatically influences the speaker recognition. Many well-known features are not
suitable for the speaker recognition as those merge the specifics of the
individual voices. Therefore, we need features accentuating the individual
differences of our voices to be able to recognise speakers reliably. This work
introduces new, speaker dependent features called Speaker Dependent Frequency
Cepstrum Coefficients (SDFCC), created for the speaker recognition purposes only.
Experimental results show their performance in comparison to the well-known
features. According to the test results, the SDFCC are, for the speaker
recognition, very useful and promising.",
  address="NEUVEDEN",
  chapter="50801",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  journal="International Journal of Security and Its Applications",
  number="1",
  volume="2010",
  year="2010",
  month="february",
  pages="31--47",
  publisher="NEUVEDEN",
  type="journal article - other"
}