Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code

Shaofei Xue, Ossama Abdel Hamid, Hui Jiang 0001, Li-Rong Dai. Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014. pages 6339-6343, IEEE, 2014. [doi]

Abstract

Abstract is missing.