SPEECH RECOGNITION USING MULTILAYER RECURRENT NEURAL PREDICTION MODELS AND HMM

J.H. Kim and S.B. Lee

References

  1. [1] L. Rabiner, Fundamentals of speech recognition (New Jersey, USA: Prentice-Hall, 1993).
  2. [2] C. Myers, L.R. Rabiner, & A.E. Rosenberg, Performance tradeoffs in dynamic time warping algorithms for isolated word recognition, IEEE Trans. on Acoustics, Speech, and Signal Processing, 28(6), 1980, 623–635. doi:10.1109/TASSP.1980.1163491
  3. [3] A. Wiabel, T. Hanazawa, G. Hinton, K. Shikano, & K. Lang, Phoneme recognition using time-delay neural network, IEEE Trans. on Acoustics Speech and Signal Processing, 37(3), 1989, 328–339. doi:10.1109/29.21701
  4. [4] L.R. Rabiner, A tutorial on hidden Markov models and selected application in speech recoginition, IEEE, 77(2), 1989, 257–286. doi:10.1109/5.18626
  5. [5] J.K. Ryu & K.M. Na, Speech recognition using recurrent neural prediction models, EUROSPEECH PROCEEDINGS, 3, 1995, 2213–2216.
  6. [6] X.Q. Guo & Z.Y. Lang, Application of fully recurrent neural networks for speech recognition, Proc. of the Int. Conf. on Signal Processing, 1, 1993, 729–731.
  7. [7] L. Rabiner, On the application of vector quantization and hidden Markov models to speaker independent isolated word recognition, Bell System Technical Joural, 62(4), 1983, 62–65.
  8. [8] R.K. Joo, A study on the data fusion of Korean digit recognition using DHMM, Korea Maritime University Master thesis, Busan, Korea, 1998.
  9. [9] C6711 DSP starter kit (DSK) (online), available at http://www.ti.com.
  10. [10] A. Hyvarinen, J. Karhunen, & E. Oja, Independent component analysis (New Jersey, USA: Wiley Inter science, 2001).

Important Links:

Go Back