T. Anastasakos;J. McDonough;J. Makhoul
-;-;-
Improving robustness of MLLR adaptation with speaker-clustered regression class trees
Computer Speech and Language
Building a highly accurate Mandarin speech recognizer with language-independent technologies and language-dependent modules
IEEE Transactions on Audio, Speech, and Language Processing
Prior-shared feature and model space speaker adaptation by consistently employing map estimation
Speech Communication
Rapid speaker adaptation in latent speaker space with non-negative matrix factorization