한국어 음성인식

  • 정차균 (포스데이타(POSDATA)기술연구소)
  • Published : 1997.09.01

Abstract

한국어 음성인식기술은 1980년대를 전후로 비약적인 발전을 하여왔다. 본 논문에서는 한국어 음성인식에 적용된 기술을 검토하고, 문제점을 고찰해서 향후 한국어 음성인식의 나아갈 방향을 조명해 본다.

Keywords

References

  1. Discrete-Time Processings of Speech Signals John R. Deller, Jr;John G. Proakis;John H. L. Hansen
  2. IEEE Signal Processing v.13 no.5 A Review of large-vocabulary continuous-speech recognition Steve Young
  3. Fundamentals of speech recognition L. Rabiner;G.-H. Juang
  4. IEEE Trans. on SAP v.3 no.4 A Comparison of signal processing front ends for automatic word recognition C. R. Jankowski Jr;Hoang-Doan H. Vo;R. P. Lippman
  5. IEEE Trans. on SAP v.2 Combining TDNN and HMM in a hybrid systems for improved continuous speech recognition C. Dugast;L. Devillers;X. Aubert
  6. IEEE Trans. on Speech and Audio Processing v.1 no.2 Connectionist probability estimators in HMM speech recognition S. Renals;N. Moran;M. Cohen;H. Franco
  7. Hidden Markov Models for Speech Recognition X.D. Huang;Y. Ariki;M.A. Jack
  8. IEEE Trans. on ASSP v.37 Modularity and scaling in large phoneme neural networks A. Waibel;H. Sawai;K. Shikano
  9. Proc. of the 1990 connectionist models summer school Equivalence proofs for multi-layer perceptron classifiers and the Bayesian discriminant function J. B. Hampshire;B. A. Pearlmutter
  10. Speech communication v.20 Automatic phone segmentation and labeling of continuous speech C.-G. Jeong;Hong Jeong