Paper: On The Use Of Tied-Mixture Distributions

ACL ID H93-1020
Title On The Use Of Tied-Mixture Distributions
Venue Human Language Technologies
Session Main Conference
Year 1993
Authors

Tied-mixture (or semi-continuous) distributions are an im- portant tool for acoustic modeling, used in many high- performance speech recognition systems today. This paper provides a survey of the work in this area, outlining the different options available for tied mixture modeling, intro- ducing algorithms for reducing training time, and provid- ing experimental results assessing the trade-offs for speaker- independent recognition on the Resource Management task. Additionally, we describe an extension of tied mixtures to segment-level distributions.