Classifiers for Synthetic Speech Detection: A Comparison

Küçük Resim Yok

Tarih

2015

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Isca-Int Speech Communication Assoc

Erişim Hakkı

info:eu-repo/semantics/closedAccess

Özet

Automatic speaker verification (ASV) systems are highly vulnerable against spoofing attacks, also known as imposture. With recent developments in speech synthesis and voice conversion technology, it has become important to detect synthesized or voice-converted speech for the security of ASV systems. In this paper, we compare five different classifiers used in speaker recognition to detect synthetic speech. Experimental results conducted on the ASVspoof 2015 dataset show that support vector machines with generalized linear discriminant kernel (GLDS-SVM) yield the best performance on the development set with the EER of 0.12 % whereas Gaussian mixture model (GMM) trained using maximum likelihood (ML) criterion with the EER of 3.01 % is superior for the evaluation set.

Açıklama

16th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2015) -- SEP 06-10, 2015 -- Dresden, GERMANY
Sahidullah, Md/0000-0002-0624-2903

Anahtar Kelimeler

spoof detection, countermeasures, speaker recognition

Kaynak

16Th Annual Conference Of The International Speech Communication Association (Interspeech 2015), Vols 1-5

WoS Q Değeri

N/A

Scopus Q Değeri

N/A

Cilt

Sayı

Künye