º»¹®/³»¿ë
Àΰ£ÀÌ »ç¿ëÇÏ´Â °¡Àå º¸ÆíÀûÀ̰í, È¿À²ÀûÀ̸ç, Æí¸®ÇÑ Åë½Å¼ö´ÜÀÎ À½¼ºÀ» ±â°è¿ÍÀÇ ÀÎÅÍÆäÀ̽º ¼ö´ÜÀ¸·Î »ç¿ëÇϰíÀÚ ÇÏ´Â ³ë·ÂÀº ÄÄÇ»ÅͰ¡ °³¹ßµÇ¸é¼ºÎÅÍ ²ÙÁØÇÏ°Ô ÁøÇàµÇ¾î¿Ô´Ù. 1950³â´ë º§ ¿¬±¸¼ÒÀÇ ´ÜÀÏÈÀÚÀÇ °í¸³¼ýÀÚ ÀνĽÇÇèÀ» ÇʵηΠ¿©·¯°¡Áö ¾Æ³¯·Î±× À½¼ºÀνĽýºÅÛÀÌ °³¹ßµÇ¾úÀ¸³ª ÀνķüÀº »ó´çÈ÷ ÀúÁ¶ÇÏ¿´´Ù. ÀÌÈÄ·Î µðÁöÅÐ À½¼ºÃ³¸®±â¼úÀÇ ¹ß´Þ°ú ÀΰøÁö´É±â¼úÀÇ °áÇÕÀ¸·Î °í¸³¾î°¡ ¾Æ´Ñ ¿¬¼Ó¾î¸¦ ÀνÄÇϰíÀÚ ÇÏ´Â °èȹÀÌ ¹Ì±¹ ±¹¹æ¼º¿¡ ÀÇÇØ 1970³â´ë ÃÊ¿¡ ¼öÇàµÇ¾ú´Ù. ¾ð¾îÇÐÀûÀÎ Áö½ÄÀÇ ±â¹Ý¾øÀÌ´Â À½¼ºÀνıâ¼úÀÇ ¹ßÀüÀÌ ºÒ°¡´ÉÇÔÀ» ±ú´Ý°í ÀΰøÁö´ÉÀû ±â¹ý¿¡ ÀÇÇØ ¾ð¾îÀÇ ¹®¹ý·Ð, Àǹ̷аú °°Àº »óÀ§°èÃþÀÇ Áö½ÄÀ» À½¼ºÀνĿ¡ ÀÌ¿ëÇϰíÀÚ ÇÏ¿´À¸³ª, Å« ¼º°ú¸¦ °ÅµÎÁö´Â ¸øÇÏ¿´´Ù. ±× 10³âÈÄ, ÆÐÅÏÀνĿ¡ ±âÃʸ¦ µÐ À½¼ºÀνİú À½ÇâÀ½¼ºÇÐ, ±¸¹®·Ð, Àǹ̷Рµî ¿©·¯°¡Áö »óÇÏÀ§ °èÅëÀÇ ±¸Ã¼ÀûÀÎ Áö½ÄÀ» ÀÌ¿ëÇÑ À½¼ºÀνĽýºÅÛÀÇ °³¹ß °èȹÀÌ ¼öÇàµÇ±â ½ÃÀÛÇÏ¿´°í, ÇöÀç´Â ¸¹Àº ¿¬±¸¼º°ú¸¦ °ÅµÎ°í ÀÖ´Ù[1]. ¹Ì±¹ÀÇ À½¼ºÀνĿ¡ ´ëÇÑ ³ë·Â°ú ÇÔ²² À¯·´ÀÇ ¿©·¯ ³ª¶óµéµµ ¿©·¯°¡Áö ±â¼úÀ» ÀÌ¿ëÇÑ À½¼ºÀνĽýºÅÛÀÇ ¿¬±¸°³¹ß¿¡ ¹ÚÂ÷¸¦ °¡Çϰí ÀÖ´Ù[2].
±¹¡¦(»ý·«)
Âü°í¹®Çå
[1] K. F. Lee, Automatic Speech Recognition / The Development of the SPHINX System, Kluwer Academic Publisher, 1989.
[2] ÀÌÁ¾¶ô, `À½¼ºÀνıâ¼úÀÇ ÇöȲ°ú Àü¸Á`, Á¦ 4ȸ ÇÑ±Û ¹× Çѱ¹¾î Á¤º¸Ã³¸®¡¡Çмú¹ßÇ¥ ³í¹®Áý, pp. 689-707, 1992.
[3] ±èÇü¼ø, `À½¼ºÀνÄ`, Á¦1ȸ À½¼ºÇÐ Çмú´ëȸ ÀÚ·áÁý, pp. 156-165, 1994.
[4] À̽¹è, ÀÌÁ¾¼®, `N-best ¹®À去ö±â¹ýÀ» Àû¿ëÇÑ ¿¬¼ÓÀ½¼º ÀνĽýºÅÛ`, Á¦13ȸ À½¼ºÅë½Å ¹× ½Åȣó¸® ¿öÅ©¼¥ ³í¹®Áý, pp. 151-154, 1996.
[5] Du-Seong Chang, Myoung-Wan Koo, `A Korean Continuous Speech Recognition System Using Dependency Grammar as a Backward Language Model,` Proceedings of Natural Language Processing Pacific Rim Symposium, Seoul, Korea, pp. 646-651, 1995.
[6] ¼Ûâȯ, À¯ÇÏÁø, ¿À¿µÈ¯, ¡°´Ü¾îÃßÃâÀ» ±â¹ÝÀ¸·Î ÇÑ À½¼º ´ëÈó¸® ½Ã½ºÅÛ¡±, Á¦ 6ȸ ÇÑ±Û ¹× Çѱ¹¾î Á¤º¸Ã³¸® Çмú¹ßÇ¥ ³í¹®Áý, pp. 313-317, 1994.
[7] R. Schwartz, S. Austin, `A Comparison of Several Approximate Algorithms for Finding Multiple (N-BEST) Sentence Hyphotheses,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Toronto, Cadana, pp. 701-704, 1991.
[8] T. Tashiro, T. Takezawa, T. Morimoto, `Efficient Chart Parsing of Speech Recognition Candidates,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Adelaide, South Australia, Vol. 2, pp. 13-16, April 1994.
[9] M. Oerder, H. Ney, `Word Graphs: An Efficient Interface Between Continuous-Speech Recognition and Language Understanding,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Minneapolis, Minnesota U.S.A., Vol. 2, pp. 119-122, April 1993.
[10] R. Schwartz, S. Austin, `A Comparison of Several Approximate Algorithms for Finding Multiple (N-BEST) Sentence Hyphotheses,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Toronto, Cadana, pp. 701-704, 1991.
[11] H. Ney, X. Aubert, `A Word Graph Algorithm for Large Vocabulary, Continuous Speech Recognition,` Proceedings of the International Conference on Spoken Language Processing, Yokohama, Japan, Vol. 3, pp. 1355-1358, Sep. 1994.
[12] K. Kita, T. Kawabata, and H. Saito, `HMM continuous speech recognition using predictive LR parsing,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, 1989.
[13] T. Hanazawa, K. Kita, S. Nakamura, T. Kawabata, and K. Shikano, `ATR HMM-LR continuous speech recognition system,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, 1990.
[14] H. Ney, `Dynamic programming parsing for context-free grammars in continuous speech recognition,` IEEE Transactions on Signal Processing, Vol. 39, No. 2, 1991.
[15] K. Lari and S. Young, `Applications of stochastic context-free grammars using the inside-outside algorithm,` Computer Speech and Language, Vol. 5, No. 3, pp. 237-257, 1991.
[16] ÀåµÎ¼º, È«¿µ±¹, ±è¿ì¼º, ±¸¸í¿Ï, ¡°ÇüÅÂ¼Ò ºÐ¼®À» »ç¿ëÇÏ´Â Çѱ¹¾î À½¼º ÀÎ½Ä ½Ã½ºÅÛ¡±, Á¦ 13ȸ À½¼ºÅë½Å ¹× ½Åȣó¸® ¿öÅ©¼¥ ³í¹®Áý, pp. 201-206, 1996.
[17] H. A. Bourlard, N. Morgan, Connectionist Speech Recognition / A Hybrid Approach, Kluwer Academic Publishers, 1994.
[18] H. Bourlard, C. J. Wellekens, `Links Between Markov Models and Multilayer Perceptrons,` IEEE Transactions On Pattern Analysis and Machine Intelligence, Vol. 12, No. 12, Dec. 1990.
[19] L. Devillers, C. Dugast, `Hybrid System Combining Expert-TDNNS and HMMs for Continuous Speech Recognition,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Adelaide, South Australia, Vol. 2, pp. 165-168, April 1994.
[20] J. Tebelskis, Speech Recognition using Neural Networks, Ph. D Thesis, CMU, May 1995.
[21] À̱ٹè, ÇÑ-ÀÏ ÀÚµ¿Å뿪½Ã½ºÅÛÀ» À§ÇÑ Çѱ¹¾î ¿¬¼Ó À½¼Ò´ÜÀ§Àνİú ÇüżҺм®ÀÇ ÅëÇÕ¿¡ °üÇÑ ¿¬±¸, Á¤º¸Åë½ÅºÎ, Ãʰí¼Ó ÀÀ¿ë ¿¬±¸ °³¹ßº¸°í¼, Æ÷Ç×°ø´ë, 1996.
[22] S. Ortmanns, H. Ney, `Experimental Analysis of the Search Space for 20000-Word Speech Recognition,` Proceedings of the EUROSPEECH, Vol. 2, pp. 901-904, Madrid, Spain, Sep. 1995.
[23] H. Ney, X. Aubert, `A Word Graph Algorithm for Large Vocabulary, Continuous Speech Recognition,` Proceedings of the International Conference on Spoken Language Processing, Yokohama, Japan, Vol. 3, pp. 1355-1358, Sep. 1994.
[24] X. Aubert, H. Ney, `Large Vocabulary Continuous Speech Recognition Using Word Graphs,` Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Detroit, Michigan U.S.A., Vol. 1, pp. 49-52, May 1995.