Robust Speaker Recognition Based on Stacked Auto-encoders

Speaker recognition is a biometric modality which utilize speaker’s speech segments to recognize identity, determining whether the test speaker belongs to one of the enrolled speakers. In order to improve the robustness of i-vector framework on cross-channel conditions and explore the nova method for applying deep learning to speaker recognition, the Stacked Auto-encoders is applied to get the abstract extraction of the i-vector instead of applying PLDA. After pre-processing and feature extraction, the speaker and channel independent speeches are employed for UBM training. The UBM is then used to extract the i-vector of the enrollment and test speech. Unlike the traditional i-vector framework, which uses linear discriminant analysis (LDA) to reduce dimension and increase the discrimination between speaker subspaces, this research use stacked auto-encoders to reconstruct the i-vector with lower dimension and different classifiers can be chosen to achieve final classification. The experimental results show that the proposed method achieves better performance than the-state-of-the-art method.