Title :
Automatic complexity control for HLDA systems
Author :
Liu, X. ; Gales, M.J.F. ; Woodland, C.
Author_Institution :
Dept. of Eng., Cambridge Univ., UK
Abstract :
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 schemes 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.
Keywords :
computational complexity; speech recognition; automatic system selection; complexity; complexity control schemes; data log-likelihoods; free parameters; vocabulary speech recognition systems; Automatic control; Bayesian methods; Control systems; Hidden Markov models; Information theory; Random variables; Speech recognition; Training data; Vocabulary; Yield estimation;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
Print_ISBN :
0-7803-7663-3
DOI :
10.1109/ICASSP.2003.1198734