Nine Issues in Speech Translation

This paper sketches the author's research in nine areas related to speech translation: interactive disambiguation (two demonstrations of highly-interactive, broad-coverage speech translation are reported); system architecture; datastructures; the interface between speech recognition and analysis; the use of natural pauses for segmenting utterances; example-based machine translation; dialogue acts; the tracking of lexical co-occurrences; and the resolution of translation mismatches.

• Type: Journal
• Year: 2000
• Where: MT
• Authors: Mark Seligman
• Keywords: Broad-coverage Speech Translation, Example-Based Machine Translation, MT 2000, Speech Translation