7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Optimization of Hidden Markov Models for Embedded Systems

Klaus Reinhard, Jochen Junkawitsch, Andreas Kie▀ling, Stefan Dobler

Ericsson Eurolab Deutschland GmbH, Germany

This paper presents a method to address a significant real life problem of embedded systems. Such systems are characterized by limited resources. Restrictions are placed on the amount of available memory for the acoustic models as well as a limited computational capacity to perform the needed distance calculations. Hence the trade-off between optimal performance and meeting such requirements needs a tailor-made HMM set solution. Starting from single densities, boosting the performance is normally done by blindly splitting model densities hence doubling the amount of memory for the acoustic models. The approach in this paper proposes an iterative length adaptation (ILA) scheme to change the model length to the needs of the acoustic events. It improves the model accuracy through a decrease of the overall acoustic distance score while minimizing the amount of additional memory for the acoustic model. The improved HMMs result in a decrease of the achieved WER out- performing the acoustic models utilizing two mixture densities per state whereas the number of model densities are only increased by 21% in comparison to the single density models.


Full Paper

Bibliographic reference.  Reinhard, Klaus / Junkawitsch, Jochen / Kie▀ling, Andreas / Dobler, Stefan (2002): "Optimization of hidden Markov models for embedded systems", In ICSLP-2002, 1597-1600.