In this paper we present a novel paradigm of Artificial Intelligent (AI) connectionist model namely committee machine architecture (CM) using Radial Basis Functions (RBFN) for speech recognition applications. The architecture and training scheme associated with the CM is presented. Then the performance evaluation based on the theory is given and the analysis results are verified for conformance. Importantly we have achieved 10 % improvement on word recognition rate over the best connectionist methods and an impressive 18.082 % over the baseline HMM. Critically the error rate is reduced by 10.61% over other connectionist models and 23.29 % over baseline HMM method.
|Title of host publication||Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing|
|Number of pages||5|
|Publication status||Published - 27 Dec 2004|
|Event||Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing - Marbella, Spain|
Duration: 1 Sep 2004 → 3 Sep 2004
|Conference||Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing|
|Period||1/09/04 → 3/09/04|