Skip to Main Content
In the past two decades, significant progress has been made in automatic speech recognition (ASR) ,  and statistical machine translation (MT) . Despite some conspicuous differences, many problems in ASR and MT are closely related and techniques in the two fields can be successfully cross-pollinated. In this lecture note, we elaborate on the fundamental connections between ASR and MT, and show that the unified ASR discriminative training paradigm recently developed and presented in  can be extended to train MT models in the same spirit.
Date of Publication: Sept. 2011