Sciweavers

13 search results - page 1 / 3
» Automatic disfluency removal for improving spoken language t...
Sort
View
ICASSP
2010
IEEE
13 years 4 months ago
Automatic disfluency removal for improving spoken language translation
Statistical machine translation (SMT) systems for spoken languages suffer from conversational speech phenomena, in particular, the presence of speech dis uencies. We examine the i...
Wen Wang, Gökhan Tür, Jing Zheng, Necip ...
COLING
2010
12 years 11 months ago
Detecting Speech Repairs Incrementally Using a Noisy Channel Approach
Unrehearsed spoken language often contains disfluencies. In order to correctly interpret a spoken utterance, any such disfluencies must be identified and removed or otherwise deal...
Simon Zwarts, Mark Johnson, Robert Dale
NAACL
2004
13 years 6 months ago
Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness ...
Joungbum Kim, Sarah E. Schwarm, Mari Ostendorf
EMNLP
2009
13 years 2 months ago
Integrating sentence- and word-level error identification for disfluency correction
While speaking spontaneously, speakers often make errors such as self-correction or false starts which interfere with the successful application of natural language processing tec...
Erin Fitzgerald, Frederick Jelinek, Keith Hall
MT
2002
297views more  MT 2002»
13 years 4 months ago
MARS: A Statistical Semantic Parsing and Generation-Based Multilingual Automatic tRanslation System
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language trans...
Yuqing Gao, Bowen Zhou, Zijian Diao, Jeffrey S. So...