Abstract
The main recognition procedure in modern HMM-based continuous speech recognition systems is Viterbi algorithm. Viterbi algorithm finds out the best acoustic sequence according to input speech in the search space using dynamic programming. In this paper, dynamic programming is replaced by a search method which is based on particle swarm optimization. The major idea is focused on generating initial population of particles as the speech segmentation vectors. The particles try to achieve the best segmentation by an updating method during iterations. In this paper, a new method of particles representation and recognition process is introduced which is consistent with the nature of continuous speech recognition. The idea was tested on bi-phone recognition and continuous speech recognition workbenches and the results show that the proposed search method reaches the performance of the Viterbi segmentation algorithm ; however, there is a slight degradation in the accuracy rate.
Similar content being viewed by others
References
Bhuriyakorn P, Punyabukkana P, Suchato A (2008) A genetic algorithm-aided Hidden Markov Model topology estimation for phoneme recognition of thai continuous speech. In: Proceedings of the 9th international conference on software engineering, artifitial intelligence, networking, and parrallel/distibuted computing, pp 475–480
Chau CW, Kwong S, Diu CK, Fahrner WR (1997) Optimization of HMM by a genetic algorithm. In: Proceedings of the international conference on acoustics, speech, and signal processing, vol 3, pp 1727–1730
Hong Q, Kwong S (2003) A training method for Hidden Markov Model with maximum model distance and genetic algorithm. In: Proceedings of IEEE international conference on neural networks and signal processing, pp 465–468
Jiang Y, Hu T, Huang C, Wu X (2006) A modified particle swarm optimization algorithm. In: Proceedings of the IEEE international conference on computational intelligence and security, pp 421–424
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of IEEE international conference on neural networks, IEEE, Piscataway, pp 1942–1948
Kwong S, Chau CW, Halang WA (1996) Genetic algorithm for optimizing the nonlinear time alignment of automatic speech recognition systems. IEEE Trans Ind Electron 43(5):559–566
Kwong S, Chau C, Tang KS (2001) Optimisation of HMM topology and its model parameters by genetic algorithms. Pattern Recogn Lett 34(2):509–522
Kwong S, He Q, Ku K, Chan T, Man K, Tang K (2002) A genetic classification error method for speech recognition. J Signal Process 82(5):737–748
Lee KF, Hon HW (1989) Speaker-independent phone recognition using Hidden Markov Models. IEEE Trans Acoust Speech Signal Process 37(11):1641–1648
Mizuta S, Nakajima K (1992) A discriminative training method for continuous mixture density hmms and its implementation to recognize noisy speech. J Acoust Soc Jpn 13(6):389–393
Murphy K (2008) Hmm toolbox for matlab. http://www.cs.ubc.ca/murphy/software/HMMhmm.html
Najkar N, Razzazi F, Sameti H (2009) A novel approach to hmm-based speech recognition system using particle swarm optimization. In: Proceedings of IEEE international conference on bio-inspired computing: theories and application, pp 1–6
Najkar N, Razzazi F, Sameti H (2010) A novel approach to hmm-based speech recognition systems using particle swarm optimization. Math Comput Model 52(11-12):1910–1920
Ney H (1991) Dynamic programming parsing for context free grammars in continuous speech recognition. IEEE Trans Signal Process 39(2):336–341
Ney H, Ortmanns S (1999) Dynamic programming search for continuous speech recognition. IEEE Signal Process Mag 16(5):64–83
Rabiner LR (1989) A tutorial on Hidden Markov Models and selected applications in speech recognition. Proc IEEE 77:257–286
Rategh S, Razzazi F, Rahmani A, Gharan S (2008) A time warping speech recognition system based on particle swarm optimization. In: Proceedings of the international conference on modeling and simulation, pp 585–590
Sajedi H, Sameti H, Beigy H, Babaali B (2007) Discriminative training of Hidden Markov Model using pso algorithm. In: Proceedings of 12th annual international CSI computer conference, pp 295–302
Shi Y, Eberhart RC (1998) A modified particle swarm optimizer. In: Proceedings of the IEEE international conference on evolutionary computation, IEEE Press, Piscataway, NJ, pp 69–73
Xue L, Yin J, Ji Z, Jiang L (2006) A particle swarm optimization for Hidden Markov Model training. In: Proceedings of the 8th international conference on signal processing, vol 1, pp 16–20
Yang F, Zhang C, Bai G (2008) A novel genetic algorithm based on tabu search for HMM optimization. In: Proceedings of the 4th international conference on natural computation, vol 4, pp 57–61
Yang F, Zhang C, Sun T (2008) Comparison of particle swarm optimization and genetic algorithm for HMM training. In: Proceedings of the international conference on pattern recognition, pp 1–4
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Najkar, N., Razzazi, F. & Sameti, H. An evolutionary decoding method for HMM-based continuous speech recognition systems using particle swarm optimization. Pattern Anal Applic 17, 327–339 (2014). https://doi.org/10.1007/s10044-012-0313-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-012-0313-7