Enhancement of a text-independent speaker verification system by using feature combination and parallel structure classifiers

Abstract

Speaker Verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under noisy conditions. On the one hand, the choice of the most appropriate acoustic features is a crucial factor for performing robust speaker verification. The acoustic parameters used in the proposed system are: Mel Frequency Cepstral Coefficients (MFCC), their first and second derivatives (Deltas and Delta-Deltas), Bark Frequency Cepstral Coefficients (BFCC), Perceptual Linear Predictive (PLP), and Relative Spectral Transform-Perceptual Linear Predictive (RASTA-PLP). In this paper, a complete comparison of different combinations of the previous features is discussed. On the other hand, the major weakness of a conventional Support Vector Machine (SVM) classifier is the use of generic traditional kernel functions to compute the distances among data points. However, the kernel function of an SVM has great influence on its performance. In this work, we propose the combination of two SVM-based classifiers with different kernel functions: Linear kernel and Gaussian Radial Basis Function (RBF) kernel with a Logistic Regression (LR) classifier. The combination is carried out by means of a parallel structure approach, in which different voting rules to take the final decision are considered. Results show that significant improvement in the performance of the SV system is achieved by using the combined features with the combined classifiers either with clean speech or in the presence of noise. Finally, to enhance the system more in noisy environments, the inclusion of the multiband noise removal technique as a preprocessing stage is proposed.

Speaker identification using hybrid subspace, deep learning and machine learning classifiers

“…Pitch frequency is a perceptual characteristic of the speech signal with physical properties denoted by F0 and is used to improve the performance of speaker identification [23,24]. Many studies use these features for speaker identification not only separately but also in combination [25][26][27][28]. In this paper, six different feature extraction approaches, namely Mel Frequency Cepstral Coefficients (MFCC)+Pitch, Gammatone Cepstral Coefficients (GTCC)+Pitch, MFCC+GTCC+Pitch+eight spectral features, spectrograms, i-vectors, and Alexnet feature vectors were used.…”

Speaker Recognition through Deep Learning Techniques

“…It enables us to use many datasets that are present in the database during the training phase. There are various kinds of databases available in this field, and a list of the databases that are used in speaker recognition specifically for speaker identification and speaker verification domain [114,[168][169][170] are given in Table 11 [58,62,89,90,103,.…”

Classification of abnormal location in medium voltage switchgears using hybrid gravitational search algorithm-artificial intelligence

“…SVM is a technique according to the theory of statistical learning applied to determine the decisive boundary via separating different classes and increasing the margin [28][29][30]. SVM is fit for non-linear data set problems and less number of training data but with huge number of input.…”