A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Automatic model complexity control using marginalized discriminative growth functions
2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721)
Selecting the model structure with the "appropriate" complexity, is a standard problem for training large vocabulary continuous speech recognition (LVCSR) systems. State-of-the-art LVCSR systems are highly complex. A wide variety of techniques may be used which alter the system complexity and word error rate (WER). Explicitly evaluating systems for all possible configurations is infeasible, hence an automatic model complexity control criterion is highly desirable. Most existing complexity
doi:10.1109/asru.2003.1318400
fatcat:fzs5zwbua5ek3m44ioc2jhugra