Henrik Heine

Learn More
During the last few years, word graphs have been gaining increasing interest within the speech community as the primary interface between speech recognizers and language processing modules. Both development and evaluation of graph-producing speech decoders require generally accepted measures of word graph quality. While the notion of recognition accuracy(More)
This paper presents a HMM speech recognition system for spontaneously spoken dialogues. It has been developed as part of the German Verbmobil project whose aim is the development of a translation support system for face{to{face conversations. The HTK-based decoder deals successfully with some of the hard problems of recognizing uent speech and reaches quite(More)
We motivate the integration of a probabilistic pronunciation model into a system for recognizing spontaneous speech and propose a possible architecture of such a model. In order to develop an environment for experiments , a simplified version employing constrained phone recognition and discrete syllable-size HMM sub-word units was implemented and evaluated.(More)
  • 1