10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Investigations on Convex Optimization Using Log-Linear HMMs for Digit String Recognition

Georg Heigold, David Rybach, Ralf Schlüter, Hermann Ney

RWTH Aachen University, Germany

Discriminative methods are an important technique to refine the acoustic model in speech recognition. Conventional discriminative training is initialized with some baseline model and the parameters are re-estimated in a separate step. This approach has proven to be successful, but it includes many heuristics, approximations, and parameters to be tuned. This tuning involves much engineering and makes it difficult to reproduce and compare experiments. In contrast to the conventional training, convex optimization techniques provide a sound approach to estimate all model parameters from scratch. Such a straight approach hopefully dispense with additional heuristics, e.g. scaling of posteriors. This paper addresses the question how well this concept using log-linear models carries over to practice. Experimental results are reported for a digit string recognition task, which allows for the investigation of this issue without approximations.

Full Paper

Bibliographic reference.  Heigold, Georg / Rybach, David / Schlüter, Ralf / Ney, Hermann (2009): "Investigations on convex optimization using log-linear HMMs for digit string recognition", In INTERSPEECH-2009, 216-219.