In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Multilayer Perceptron (MLP)) is itself replaced by a Multi Gaussian HMM (MGM). Both systems represent the most widely used statistical models for robust ASR (automatic speech recognition). It is shown how the FC formula for the likelihood-based MGMs can easily be derived from the posterior-based approach by simply applying BayesÂ’ Rule. The experiments show that the Full Combination multi-band system with MGM experts performs better, in all noise conditions tested, than the simple sum and product rules which are normally used. As compared to the baseline full-band system, the FC system shows increased robustness mainly on band-limited noise. The goal of this article is not a performance comparison between Multilayer Perceptrons and Multi Gaussian Models but between the theory of the two approaches, posterior-based vs. likelihood-based FC approach, so results are only given for the MGMs.
Cite as: Hagen, A., Morris, A. (2000) Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 345-348, doi: 10.21437/ICSLP.2000-86
@inproceedings{hagen00_icslp,
author={Astrid Hagen and Andrew Morris},
title={{Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 1, 345-348},
doi={10.21437/ICSLP.2000-86}
}