Visualization of equations in an interactive environment
D. Watson, J. Wejchert, et al.
VIS 1991
A speaker adaptation strategy is described that is based on finding a subset of speakers, from the training set, who are acoustically close to the test speaker, and using only the data from these speakers (rather than the complete training corpus) to reestimate the system parameters. Further, a linear transformation is computed for every one of the selected training speakers to better map the training speaker's data to the test speaker's acoustic space. Finally, the system parameters (Gaussian means) are reestimated specifically for the test speaker using the transformed data from the selected training speakers. Experiments showed that this scheme is capable of providing an 18% relative improvement in the error rate on a large-vocabulary task with the use of as little as three sentences of adaptation data. © 1998 IEEE.
D. Watson, J. Wejchert, et al.
VIS 1991
Srideepika Jayaraman, Chandra Reddy, et al.
Big Data 2021
Jehanzeb Mirza, Leonid Karlinsky, et al.
NeurIPS 2023
Konstantinos Tarabanis, Roger Y. Tsai, et al.
Computer Vision and Image Understanding