Text-independent Speaker Identification Method Research Articles

Deep CNNs With Self-Attention for Speaker Identification

Most current works on speaker identification are based on i-vector methods; however, there is a marked shift from the traditional i-vector to deep learning methods, especially in the form of convolutional neural networks (CNNs). Rather than designing features and a subsequent individual classification model, we address the problem by learning features and recognition systems using deep neural networks. Based on the deep convolutional neural network (CNN), this paper presents a novel text-independent speaker identification method for speaker separation. Specifically, this paper is based on the two representative CNNs, called the visual geometry group (VGG) nets and residual neural networks (ResNets). Unlike prior deep neural network-based speaker identification methods that usually rely on a temporal maximum or average pooling across all time steps to map variable-length utterances to a fixed-dimension vector, this paper equips these two CNNs with a structured self-attention mechanism to learn a weighted average across all time steps. Using the structured self-attention layer with multiple attention hops, the proposed deep CNN network is not only capable of handling variable-length segments but also able to learn speaker characteristics from different aspects of the input sequence. The experimental results on the speaker identification benchmark database, VoxCeleb demonstrate the superiority of the proposed method over the traditional i-vector-based methods and the other strong CNN baselines. In addition, the results suggest that it is possible to cluster unknown speakers using the activation of an upper layer of a pre-trained identification CNN as a speaker embedding vector.

Factor analysis method for text-independent speaker identification

Factor analysis method offers state-of-the-art performance in speaker identification during the paper. The compact representations of speakers named i-vectors are extracted from the utterances in a new low dimensional speaker- and channel-dependent space, referred to a total variability space. LBG algorithm is combined with fuzzy theory in the initialization of speaker models，which helps improve the recognition rate of the system. Channel compensation techniques, such as Linear Discriminate Analysis (LDA), Principal Component Analysis (PCA), Nuisance Attribute Projection (NAP) and Within-class Covariance Normalization (WCCN) are compared during the experiment. It can be seen that LDA followed by WCCN achieves satisfying performance. In addition, experiments contrast several identification methods. One is through Support-Vector-Machine (SVM), another one directly uses the cosine distance similarity (CDS) as the final decision score, logarithmic likelihood and vector quantization are used to compare to above two methods. It demonstrates that CDS combined with score normalization obtains better result. The testing of mobile phone database shows the robustness of the system in complex channel environment. The graphical user interface of training and testing module is simulated on MATLAB in the end of the paper.

The Use of Group Delay Features of Linear Prediction Model for Speaker Recognition

New text independent speaker identification method is presented. Phase spectrum of all-pole linear prediction (LP) model is used to derive the speech features. The features are represented by pairs...

The Use of Group Delay Features of Linear Prediction Model for Speaker Recognition

New text independent speaker identification method is presented. Phase spectrum of all-pole linear prediction (LP) model is used to derive the speech features. The features are represented by pairs of numbers that are calculated from group delay extremums of LP model spectrum. The first component of the pair is an argument of maximum of group delay of all pole LP model spectrum and the second is an estimation of spectrum bandwidth at the point of spectrum extremum. A similarity metric that uses group delay features is introduced. The metric is adapted for text independent speaker identification with general assumption that test speech channel may contain multiple speakers. It is demonstrated that automatic speaker recognition system with proposed features and similarity metric outperforms systems based on Gaussian mixture model with Mel frequency cepstral coefficients, formants, antiformants and pitch features.