14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

Simultaneous Perturbation Stochastic Approximation for Automatic Speech Recognition

Daniel Stein, Jochen Schwenninger, Michael Stadtschnitzer

Fraunhofer IAIS, Germany

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.

Full Paper

Bibliographic reference.  Stein, Daniel / Schwenninger, Jochen / Stadtschnitzer, Michael (2013): "Simultaneous perturbation stochastic approximation for automatic speech recognition", In INTERSPEECH-2013, 622-626.