Robust Support Vector Machines for Speaker Verification Task
An important step in speaker verification is extracting features
that best characterize the speaker voice. This paper investigates
a front-end processing that aims at improving the performance
of speaker verification based on the SVMs classifier, in text
independent mode. This approach combines features based on
conventional Mel-cepstral Coefficients (MFCCs)and Line Spectral
Frequencies (LSFs) to constitute robust multivariate feature
vectors. To reduce the high dimensionality required for training
these feature vectors, we use a dimension reduction method
called principal component analysis (PCA). In order to evaluate
the robustness of these systems, different noisy environments
have been used. The obtained results using TIMIT database
showed that, using the paradigm that combines these spectral
cues leads to a significant improvement in verification accuracy,
especially with PCA reduction for low signal-to-noise ratio
noisy environment.
Keywords: SVM, LSF, MFCC, Noisy environment, PCA.
Download Full-Text
ABOUT THE AUTHORS
Kawthar Yasmine Zergat
Received her Master II degree in Communication and Multimedia from the University of Science and Technology Houari Boumedienne (USTHB), Algiers in 2010. Currently, she is pursuing the Ph.D. degree in, Telecommunications and Information Processing in the Communication Systems and Speech Processing Laboratory, USTHB. Her current research concentrates on robust speaker recognition and speech processing.
Abderrahmane Amrouche
Was born in Algeria. He received his “diplome d’ingenieur” (engineer degree) in Electronics from the National Polytechnic school of Algiers in 1980. He received his “Magister” degree in 1995 and Doctorat d’Etat” (Ph.D) in Real Time Systems in 2007 from the University of Science and Technology Houari Boumedienne (USTHB). He is an Assistant Professor in Communication Systems and Speech Processing Laboratory, USTHB. His research interests include pattern recognition, speech processing, Multilingual speech recognition, neural networks, prosodic modelling.
Kawthar Yasmine Zergat
Received her Master II degree in Communication and Multimedia from the University of Science and Technology Houari Boumedienne (USTHB), Algiers in 2010. Currently, she is pursuing the Ph.D. degree in, Telecommunications and Information Processing in the Communication Systems and Speech Processing Laboratory, USTHB. Her current research concentrates on robust speaker recognition and speech processing.
Abderrahmane Amrouche
Was born in Algeria. He received his “diplome d’ingenieur” (engineer degree) in Electronics from the National Polytechnic school of Algiers in 1980. He received his “Magister” degree in 1995 and Doctorat d’Etat” (Ph.D) in Real Time Systems in 2007 from the University of Science and Technology Houari Boumedienne (USTHB). He is an Assistant Professor in Communication Systems and Speech Processing Laboratory, USTHB. His research interests include pattern recognition, speech processing, Multilingual speech recognition, neural networks, prosodic modelling.
