Automatic complexity control for HLDA systems

X. Liu, M.J.F. Gales, P.C. Woodland
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).  
Designing a state-of-the-art large vocabulary speech recognition systems is a highly complex problem. A wide range of techniques are available that affect the performance and number of free parameters. Selecting the appropriate complexity of system is both time-consuming and only a limited number of possible systems can be examined. This paper presents initial results on automatic system selection when both the number of dimensions and the number of components vary. Various complexity control
more » ... hemes are discussed and evaluated. Limitations of schemes based on predicting held-out data log-likelihoods are described. In addition, problems of standard approximations for this task are detailed.
doi:10.1109/icassp.2003.1198734 dblp:conf/icassp/LiuGW03 fatcat:xymhzjxhsjedpjfhmyvwubqq2m