The application of Speech Recognition Technology based on HMM
作者： Guilin Yan
DOI: 10.2991/ICISMME-15.2015.139
关键词: Pattern recognition 、 Speech recognition 、 Speaker recognition 、 SIGNAL (programming language) 、 Artificial intelligence 、 Hidden Markov model 、 Computer science 、 Viterbi algorithm 、 Interpretation (logic) 、 Acoustic model
摘要: It was a great improvement for the speech signal digital processing technology to use model of Hidden Markov Model in 1980's, which is used describe signal. In this paper, with help recognition and interpretation model, by means analysis on HMM Viterbi algorithm, it discusses based HMM.
sci-hub.st 参考文章(5)
J. Salazar, M. Robinson, M.R. Azimi-Sadjadi, A hybrid HMM-neural network with gradient descent parameter training international joint conference on neural network. ,vol. 2, pp. 1086- 1091 ,(2003) , 10.1109/IJCNN.2003.1223842
Shingo Yoshizawa, Yoshikazu Miyanaga, Norinobu Yoshida, A high-speed HMM VLSI module with block parallel processing Electronics and Communications in Japan (Part III: Fundamental Electronic Science). ,vol. 87, pp. 12- 23 ,(2004) , 10.1002/ECJC.10099
Tze Fen Li, Speech recognition of mandarin monosyllables Pattern Recognition. ,vol. 36, pp. 2713- 2721 ,(2003) , 10.1016/S0031-3203(03)00135-3
R. Hoffmann, C.-M. Westendorf, The development of analysis methods for speech recognition Behavioural Processes. ,vol. 39, pp. 113- 125 ,(1997) , 10.1016/S0376-6357(96)00055-1
H. Hermansky, B. Hanson, H. Wakita, Perceptually based linear predictive analysis of speech international conference on acoustics, speech, and signal processing. ,vol. 10, pp. 509- 512 ,(1985) , 10.1109/ICASSP.1985.1168384