Speech recognition using a strong correlation assumption for the instantaneous spectra
暂无分享,去创建一个
[1] Martin Russell,et al. A segmental HMM for speech pattern modelling , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[2] Patrick Kenny,et al. A linear predictive HMM for vector-valued observations with applications to speech recognition , 1990, IEEE Trans. Acoust. Speech Signal Process..
[3] George Zavaliagkos,et al. A hybrid segmental neural net/hidden Markov model system for continuous speech recognition , 1994, IEEE Trans. Speech Audio Process..
[4] Mari Ostendorf,et al. A stochastic segment model for phoneme-based continuous speech recognition , 1989, IEEE Trans. Acoust. Speech Signal Process..
[5] Kuldip K. Paliwal,et al. Use of temporal correlation between successive frames in a hidden Markov model based speech recognizer , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[6] Oded Ghitza,et al. Hidden Markov models with templates as non-stationary states: an application to speech recognition , 1993, Comput. Speech Lang..
[7] Mari Ostendorf,et al. A Dynamical System Approach to Continuous Speech Recognition , 1991, HLT.
[8] Francis Jack Smith,et al. A hidden Markov model with optimized inter-frame dependence , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.