Learn about discriminative training of acoustic models in this 37-minute lecture from IBM researcher Daniel Povey at Johns Hopkins University's Center for Language & Speech Processing. Gain insights into Maximum Mutual Information Estimation (MPE) techniques and discover fMPE, an innovative feature-space transformation method developed at IBM that maximizes the MPE criterion for acoustic model training.
Discriminative Training of Acoustic Models - From MPE to fMPE
Center for Language & Speech Processing(CLSP), JHU via YouTube
Overview
Syllabus
Old and new work in discriminative training of acoustic models – Daniel Povey (IBM) - 2005
Taught by
Center for Language & Speech Processing(CLSP), JHU
Related Courses
-
UBM-based Acoustic Modeling for ASR - 2009
-
Recent Progress in Acoustic Speaker and Language Recognition - October 2013
-
Speech Recognition - 2000
-
An Implementation of Sub-Space Model Based Automatic Speech Recognition - 2009
-
Extracting Speaker and Emotion Information from Self-Supervised Speech Models
