This paper describes an incremental approach to parsing transcribed spontaneous speech containing disfluencies with a Hierarchical Hidden Markov Model (HHMM). This model makes use...
It has always been difficult for language understanding systems to handle spontaneous speech with satisfactory robustness, primarily due to such problems as the fragments, disflue...
Bor-shen Lin, Berlin Chen, Hsin-Min Wang, Lin-Shan...
In this paper, we present a chunk based partial parsing system for spontaneous, conversational speech in unrestricted domains. We show that the chunk parses produced by this parsi...
The German joint research project Verbmobil (VM) aims at the deveh)pment of a speech to speech translation system. This paper reports on research done in our group which belongs t...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to ...