An experimental environment for the generation and verification of word hypotheses in continuous speech

We present a flexible environment for the generation of word hypotheses in continuous speech. After describing the interface to the other modules of our speech understanding system a verification algorithm and a word spotting technique both based on HMM will be discussed. The generation of reference models for the matching procedures is done automatically using the standard pronunciation of a word and a set of phonological rules about intra word assimilation. These alternative pronunciations are represented by graphs with labeled edges. Some preliminary results for the matching procedures are also given.