KMID : 1022420120040030095
|
|
Phonetics and Speech Sciences 2012 Volume.4 No. 3 p.95 ~ p.101
|
|
Forensic Automatic Speaker Identification System for Korean Speakers
|
|
Kim Kyung-Wha
So Byung-Min Yu Ha-Jin
|
|
Abstract
|
|
|
In this paper, we introduce the automatic speaker identification system ¡®SPO(Supreme Prosecutors Office) Verifier¡¯. SPO Verifier is a GMM(Gaussian mixture model)-UBM(universal background model) based automatic speaker recognition system and has been developed using Korean speakers¡¯ utterances. This system uses a channel compensation algorithm to compensate recording device characteristics. The system can give the users the ability to manage reference models with utterances from various environments to get more accurate recognition results. To evaluate the performance of SPO Verifier on Korean speakers, we compared this system with one of the most widely used commercial systems in the forensic field. The results showed that SPO Verifier shows lower EER(equal error rate) than that of the commercial system.
|
|
KEYWORD
|
|
forensic phonetics, automatic speaker recognition system, speaker verification, speaker identification, GMM-UBM
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|