Probabilistic cooperation of connectionist expert modules: validation on a speaker identification task

• Authors: Younès Bennani
• Venue: ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
• Year: 1993

This paper presents and evaluates a modular connectionist system for speaker identification. Modularity has emerged as a powerful technique for reducing the complexity of connectionist systems, and allowing a priori knowledge to be incorporated into their design. Thus, for systems where the amount of training data is limited, modular systems incorporating a priori knowledge are likely to generalize significantly better than a monolithic connectionist system. An architecture is developed in this paper which achieves speaker identification based on the cooperation of several connectionist expert modules. When tested on a population of 102 speakers extracted from the DARPA-TIMIT database, perfect identification was observed. In a specific comparison with a system based on Multivariate Auto-Regressive Models, the modular connectionist approach was found to be significantly better in terms of both identification accuracy and speed.