In this paper we present an integrated approach for recognizing both the word sequence and the syntactic-prosodic structure of a spontaneous utterance. We take into account the fact that a spontaneous utterance is not merely an unstructured sequence of words by incorporating phrase boundary information into the language model and by providing HMMs to model boundaries. This allows for a distinction between word transitions across phrase boundaries and transitions within a phrase. During recognition, the syntactic-prosodic structure of the utterance is determined implicitly. Without any increase in computational effort, this leads to a 4% reduction of word error rate, and, at the same time, syntactic-prosodic boundary labels are provided for subsequent processing. The boundaries are recognized with a precision and recall rate of about 75% each. They can be used to reduce drastically the computational effort for parsing spontaneous utterances. We also present a system architecture to incorporate additional prosodic information.
Cite as: Gallwitz, F., Batliner, A., Buckow, J., Huber, R., Niemann, H., Nöth, E. (1998) Integrated recognition of words and phrase boundaries. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0328, doi: 10.21437/ICSLP.1998-160
@inproceedings{gallwitz98_icslp, author={Florian Gallwitz and Anton Batliner and Jan Buckow and Richard Huber and Heinrich Niemann and Elmar Nöth}, title={{Integrated recognition of words and phrase boundaries}}, year=1998, booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)}, pages={paper 0328}, doi={10.21437/ICSLP.1998-160} }