This paper focuses on the problem of finding a set of Hidden Markov Models that can be trained to model context dependencies with good statistical accuracy, given the constraint of a fixed amount of training data. Two aspects have been investigated in this work: clustering of intra-word context-dependent units with similar contexts on the basis of different similarity measures, and definition of inter-word coarticulation units. A Dynamic Programming procedure is presented that allows a large set of context-dependent units to be clustered into a given number of units while optimizing a global cost measure. Inter-word units were found to provide better phonetic representations of word junctures and to increase recognition accuracy, though less than it has been reported for the English language.
Bibliographic reference. Fissore, Lorenzo / Giachin, Egidio P. / Laface, P. / Micca, G. (1991): "Selection of speech units for a speaker-independent CSR task", In EUROSPEECH-1991, 1389-1392.