Welcome to the Speech WebOverviewThe general idea of our speech project is to improve speech recognition performance by analysing and modeling topologies of continuous Hidden Markov Models. The basic idea is to model the topologies data driven through novel heuristics which let us evaluating the phone HMM qualities without doing a recognition experiment. We study our approaches on the German part of the VERBMOBIL corpus.ContentsNote: You must be in the SpeechGroup to edit the Speech webRecent Changes
| ||||||||||||||||||||||
Copyright (c) 1999-2006 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.