In recent years, techniques of output combination from multiple speech recognizers for improved overall performance have gained popularity. Most commonly, the combined systems are established independently. This paper describes our attempt to directly target joint system performance in the discriminative training objective of acoustic model parameter estimation. It also states first promising results.
Bibliographic reference. Willett, Daniel / He, Chuang (2008): "Discriminative training for complementariness in system combination", In INTERSPEECH-2008, 919.