Cache language model
In computer science, a cache language model is a fundamental statistical speech recognition method upon which many speech recognition technologies crucially depend. Models of this type incorporate a cache component in which patterns of word use can be discovered so as to facilitate word prediction and minimize word error rates.[1][2][3][4]
References
- ^ http://visgraph.cs.ust.hk/biometrics/Papers/Voice/pami1990-06-01.pdf
- ^ http://www.ece.umassd.edu/Faculty/acosta/ICASSP/Icassp_1997/pdf/scan/ic970799.pdf
- ^ http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5495011
- ^ http://www.imt.liu.se/mi_old/Intern/Onlineproceedings/ICASSP_2010/pdfs/0005194.pdf
Further reading
- Jelinek, Frederick. Statistical Methods for Speech Recognition. (The MIT Press, 1997).