This a matlab toolkit of different methods for i-vector extraction.
Universal approach for i-vector extraction, e.g., FEFA, FA, PPCA.
A speaker recognition demo by using FA.
A partial least squares (PLS) based i-vector extraction method.
Chen Chen, Jiqing Han. Partial least squares based total variability space modeling for i-vector speaker verification[J]. Chinese Journal of Electronics. 2018, 27(6): 1229-1233.
A probabilistic partial least squares (PPLS) based i-vector extraction method.
Chen Chen, Jiqing Han, Yilin Pan. Speaker verification via estimating total variability space using probabilistic partial least squares[C]. Annual Conference of the International Speech Communication Association (INTERSPEECH), 2017: 1537-1541.
A Bayesian principal component analysis (BPCA) based i-vector extraction method.
Yafeng Rong, Chen Chen, Deyun Chen, Yongjun He. Bayesian principal component analysis for i-vector speaker verification[J]. Acta Electronica Sinica, 2021,49(11): 2186-2194.
A common latent representation learning (CLRL) based i-vector extraction method.
Chen Chen, Yulin Bu, Yong Chen, Deyun Chen. Common latent representation learning for low-resourced spoken language identification[J]. Multimedia Tools and Applications, 2023.