A Shrinkage Estimator for Speech Recognition with Full Covariance HMMs

P. Bell, S. King

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We consider the problem of parameter estimation in full-covariance Gaussian mixture systems for automatic speech recognition. Due to the high dimensionality of the acoustic feature vector, the standard sample covariance matrix has a high variance and is often poorly-conditioned when the amount of training data is limited. We explain how the use of a shrinkage estimator can solve these problems, and derive a formula for the optimal shrinkage intensity. We present results of experiments on a phone recognition task, showing that the estimator gives a performance improvement over a standard full-covariance system
Original languageEnglish
Title of host publicationProc. Interspeech
Publication statusPublished - Sept 2008


Dive into the research topics of 'A Shrinkage Estimator for Speech Recognition with Full Covariance HMMs'. Together they form a unique fingerprint.

Cite this