ISCA Archive Eurospeech 2003
ISCA Archive Eurospeech 2003

Context-dependent output densities for hidden Markov models in speech recognition

Georg Stemmer, Viktor Zeissler, Christian Hacker, Elmar Nöth, Heinrich Niemann

In this paper we propose an efficient method to utilize context in the output densities of HMMs. State scores of a phone recognizer are integrated into the HMMs of a word recognizer which makes their output densities context-dependent. A significant reduction of the word error rate has been achieved when the approach is evaluated on a set of spontaneous speech utterances. As we can expect that context is more important for some phone models than for others, we further extend the approach by state-dependent weighting factors which are used to control the influence of the different information sources. A small additional improvement has been achieved.