Robust speaker identification and verification

Jia Ching Wang, Chung Hsien Yang, Jhing Fa Wang, Hsiao Ping Lee

Research output: Contribution to journalArticlepeer-review

25 Scopus citations


Acoustic characteristics have played an essential role in biometrics. In this article, we introduce a robust, text-independent speaker identification/verification system. This system is mainly based on a subspace-based enhancement technique and probabilistic support vector machines (SVMs). First, a perceptual filterbank is created from a psycho-acoustic model into which the subspace-based enhancement technique is incorporated. We use the prior SNR of each subband within the perceptual filterbank to decide the estimator's gain to effectively suppress environmental background noises. Then, probabilistic SVMs identify or verify the speaker from the enhanced speech. The superiority of the proposed system has been demonstrated by twenty speaker data taken from AURORA-2 database with added background noises.

Original languageEnglish
Pages (from-to)52-59
Number of pages8
JournalIEEE Computational Intelligence Magazine
Issue number2
StatePublished - May 2007


Dive into the research topics of 'Robust speaker identification and verification'. Together they form a unique fingerprint.

Cite this