Dataset shift compensation in machine learning

A method comprising:

• operating at least one hardware processor of a PLDA (Probabilistic Linear Discriminant Analysis) speaker recognition system to compensate for inter-dataset variability, by:
• receiving a heterogeneous development dataset comprising multiple speech samples;
• dividing the multiple speech samples into multiple homogenous subsets;
• for each subset i of the multiple homogenous subsets:
• (a) estimating PLDA hyper-parameters {μi, Bi, Wi}, wherein μ denotes a center of an i-vector space, B denotes a between-speaker covariance matrix and W denotes a within-speaker covariance matrix, and (b) computing an i-vector subspace Sμ corresponding to {μi}, an i-vector subspace SW corresponding to {Wi}, and an i-vector subspace SB corresponding to {Bi};
• joining i-vector subspaces Sμ, SW and SB into a single subspace S;
• removing subspace S from i-vectors of the multiple speech samples, to produce denoised speech samples;
• training the PLDA speaker recognition system using the denoised speech samples;
• and
• performing speaker recognition using the trained PLDA speaker recognition system.

A computer program product for inter-dataset variability compensation for speaker recognition, the computer program product comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by at least one hardware processor of a PLDA (Probabilistic Linear Discriminant Analysis) speaker recognition system to:

• compensate for inter-dataset variability in the PLDA speaker recognition system, by:
• receiving a heterogeneous development dataset comprising multiple speech samples;
• dividing the multiple speech samples into multiple homogenous subsets;
• for each subset i of the multiple homogenous subsets:
• (a) estimating PLDA (Probabilistic Linear Discriminant Analysis) hyper-parameters {μi, Bi, Wi}, wherein μ denotes a center of an i-vector space, B denotes a between-speaker covariance matrix and W denotes a within-speaker covariance matrix, and (b) computing an i-vector subspace Sμ corresponding to {μi}, an i-vector subspace SW corresponding to {Wi}, and an i-vector subspace SB corresponding to {Bi};
• joining i-vector subspaces Sμ, SW and SB into a single subspace S;
• removing subspace S from i-vectors of the multiple speech samples, to produce denoised speech samples;
• training the PLDA speaker recognition system using the denoised speech samples;
• and
• performing speaker recognition using the trained PLDA speaker recognition system.