Network and System Security, International Conference on (2009)
Gold Coast, Queensland, Australia
Oct. 19, 2009 to Oct. 21, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/NSS.2009.44
This paper proposes a genetic algorithm (GA) based beamformer to optimize speech recognition accuracy for a pretrained speech recognizer. The proposed beamformer is designed to tackle the non-differentiable and non-linear natures of speech recognition by employing the GA algorithm to search for the optimal beamformer weights. Specifically, a population of beamformer weights is reproduced by crossover and mutation until the optimal beamformer weights are obtained. Results show that the speech recognition accuracies can be greatly improved even in noisy environments.
Speech recognition, beamforming, signal enhancement, genetic algorithm
K. Chan, S. Nordholm, K. Yiu, S. Low and S. Ling, "Speech Recognition Enhancement Using Beamforming and a Genetic Algorithm," Network and System Security, International Conference on(NSS), Gold Coast, Queensland, Australia, 2009, pp. 510-515.