Improvement in safety of formant method of text dependent verification of a speaker by a new method of segmentation of speech signal

Download article in PDF format

Authors: Ruchay A. N.

Annotation: The new method of segmentation of speech signal is introduced in this article, it improves the safety of the formant method of text dependent verification of a speaker. The new method is based on an exponent of signal singularity.

Keywords: speaker recognition, text dependent speaker verification, formant, false acceptance and rejection rate, segmentation of speech signal, singularity, holder exponent, continuous wavelet transform

Viktor N. Maslennikov

Executive Secretary of the Editor’s Office

 Editor’s Office: 40 Lenina Prospect, Tomsk, 634050, Russia

  Phone / Fax: + 7 (3822) 51-21-21 / 51-43-02

  vnmas@tusur.ru

Subscription for updates