Robust Support Vector Machines for Speaker Verification Task
This work addresses speaker verification robustness for noisy conditions, but it is incremental as it builds on existing feature and reduction methods.
The paper tackled speaker verification in noisy environments by combining MFCC and LSF features with PCA for dimensionality reduction, achieving significant accuracy improvements, particularly at low signal-to-noise ratios.
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.