9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Discriminative Training for Complementariness in System Combination

Daniel Willett (1), Chuang He (2)

(1) Nuance Communications, Germany; (2) Nuance Communications, USA

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.

Full Paper

Bibliographic reference.  Willett, Daniel / He, Chuang (2008): "Discriminative training for complementariness in system combination", In INTERSPEECH-2008, 919.