RAPID FEATURE SPACE MLLR SPEAKER ADAPTATION WITH BILINEAR MODELS
Adaptation for ASR
Presented by: Jie Zhou, Author(s): Shilei Zhang, IBM Research Lab - China, China; Peder Olsen, IBM T.J. Watson Research Center, United States; Yong Qin, IBM Research Lab - China, China
In this paper, we propose a novel method for rapid feature space Maximum Likelihood Linear Regression (FMLLR) speaker adaptation based on bilinear models. When the amount of adaptation data is limited, the conventional FMLLR transforms can be easily over-trained and can even degrade the performance. In such cases, usually by introducing structural constraints on the FMLLR transformation, the original FMLLR adaptation method can be modified for rapid adaptation. The objective of our bilinear model is to introduce a prior knowledge analysis on the training speakers based on Singular Vector Decomposition (SVD), and to incorporate it in the decoding process. This can effectively reduce the number of free parameters of FMLLR transformation and achieve performance improvements even with limited adaptation data. The efficiency of the proposed algorithm is demonstrated with experiments on the Mandarin digital dataset and the Mandarin voice search dataset respectively.