Unsupervised training in natural language call routing
作者： Daniel J. McCarthy , Premkumar Natarajan
DOI:
关键词:
摘要: A method of training a natural language call routing system using an unsupervised trainer is provided. The adapted to tune performance the on basis feedback and new topic information. comprises: storing audio data from incoming as well associated unique identifier information for call; applying highly accurate speech recognizer waveform database produce text transcription stored forwarding outputs second database, being store transcripts with respective identifiers data; routed by router agent: entering determined agent into form; supplying form together identifier; automated fulfillment: querying caller regarding true adding this information, identifier, database; performing identification model statistical grammar in database.
google.com.ph 参考文章(8)
Kenney Ng, Man-Hung Siu, Herbert Gish, Philippe Jeanrenaud, Jan Robin Rohlicek, Phonetic-based word spotter: various configurations and application to event spotting. conference of the international speech communication association. ,(1993)
Frederick Jelinek, Statistical methods for speech recognition ,(1997)
S. Kullback, R. A. Leibler, On Information and Sufficiency Annals of Mathematical Statistics. ,vol. 22, pp. 79- 86 ,(1951) , 10.1214/AOMS/1177729694
P. Placeway, R. Schwartz, P. Fung, L. Nguyen, The estimation of powerful language models from small and large corpora IEEE International Conference on Acoustics Speech and Signal Processing. ,vol. 2, pp. 33- 36 ,(1993) , 10.1109/ICASSP.1993.319222
A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum Likelihood from Incomplete Data Via theEMAlgorithm Journal of the Royal Statistical Society: Series B (Methodological). ,vol. 39, pp. 1- 22 ,(1977) , 10.1111/J.2517-6161.1977.TB01600.X
Richard M. Schwartz, Long Nguyen, Single tree method for grammar directed, very large vocabulary speech recognizer The Journal of the Acoustical Society of America. ,vol. 102, pp. 3253- ,(1997) , 10.1121/1.420245
J. Golden, O. Kimball, Man-Hung Siu, H. Gish, Automatic topic identification for two-level call routing international conference on acoustics speech and signal processing. ,vol. 1, pp. 509- 512 ,(1999) , 10.1109/ICASSP.1999.758174
J.R. Rohlicek, P. Jeanrenaud, K. Ng, H. Gish, B. Musicus, M. Siu, Phonetic training and language modeling for word spotting IEEE International Conference on Acoustics Speech and Signal Processing. ,vol. 2, pp. 459- 462 ,(1993) , 10.1109/ICASSP.1993.319340