University of science and technology of China, Hefei, China

---

Abstract—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, named a total variability space. LBG algorithm is combined with fuzzy theory in the initialization of speaker models,which improves 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, several identification methods are contrasted in the experiments. 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.

Index Terms—factor analysis, total space, i-vector, channel compensation, cosine similarity, score normalization

[PDF]

Cite: Tingting Liu, Shengxiao Guan, "Factor Analysis Method for Text-independent Speaker Identification," Journal of Software vol. 9, no. 11, pp. 2851-2860, 2014.