While both the acoustic model and the language model in automatic speech recognition are typically well-trained on the target domain, the free parameters of the decoder itself are often set manually. In this paper, we investigate in how far a stochastic approximation algorithm can be employed to automatically determine the best parameters, especially if additional time-constraints are given on unknown machine architectures. We offer our findings on the German Difficult Speech Corpus, and present significant improvements over both the spontaneous and planned clean speech task.
Bibliographic reference. Stein, Daniel / Schwenninger, Jochen / Stadtschnitzer, Michael (2013): "Simultaneous perturbation stochastic approximation for automatic speech recognition", In INTERSPEECH-2013, 622-626.