A genetic classification error method for speech recognition
Signal Processing
Optimization of HMM by a Genetic Algorithm
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3
A Time Warping Speech Recognition System Based on Particle Swarm Optimization
AMS '08 Proceedings of the 2008 Second Asia International Conference on Modelling & Simulation (AMS)
SNPD '08 Proceedings of the 2008 Ninth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing
A Novel Genetic Algorithm Based on Tabu Search for HMM Optimization
ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 04
Dynamic programming parsing for context-free grammars in continuousspeech recognition
IEEE Transactions on Signal Processing
Filterbank optimization for robust ASR using GA and PSO
International Journal of Speech Technology
Hi-index | 0.98 |
The main core of HMM-based speech recognition systems is Viterbi algorithm. Viterbi algorithm uses dynamic programming to find out the best alignment between the input speech and a given speech model. In this paper, dynamic programming is replaced by a search method which is based on particle swarm optimization algorithm. The major idea is focused on generating an initial population of segmentation vectors in the solution search space and improving the location of segments by an updating algorithm. Several methods are introduced and evaluated for the representation of particles and their corresponding movement structures. In addition, two segmentation strategies are explored. The first method is the standard segmentation which tries to maximize the likelihood function for each competing acoustic model separately. In the next method, a global segmentation tied between several models and the system tries to optimize the likelihood using a common tied segmentation. The results show that the effect of these factors is noticeable in finding the global optimum while maintaining the system accuracy. The idea was tested on an isolated word recognition and phone classification tasks and shows its significant performance in both accuracy and computational complexity aspects.