Title :
Modeling Successive Frame Dependencies with Hybrid HMM/BN Acoustic Model
Author :
Markov, Konstantin ; Nakamura, Satoshi
Author_Institution :
Dept. of Acoust. & Speech Res., Adv. Telecommun. Res. Inst. Int., Kyoto, Japan
fDate :
March 18-23, 2005
Keywords :
acoustic signal processing; belief networks; hidden Markov models; learning (artificial intelligence); speech recognition; statistical distributions; Bayesian network; Gaussian mixture HMM; HMM state; LVCSR system; continuous word recognition; feature vector; hidden Markov model; hybrid acoustic model; phoneme recognition; speech recognition systems; speech vector; state probability distribution; successive frame dependencies; Acoustics; Automatic speech recognition; Bayesian methods; Hidden Markov models; Natural languages; Parametric statistics; Probability distribution; Speech recognition; Stochastic processes; Training data;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415210
