Title :
Statistical Phrase-Based Speech Translation
Author :
Mathias, Lambert ; Byrne, William
Author_Institution :
Center for Language & Speech Process., Johns Hopkins Univ.
Abstract :
A generative statistical model of speech-to-text translation is developed as an extension of existing models of phrase-based text translation. Speech is translated by mapping ASR word lattices to lattices of phrase sequences which are then translated using operations developed for text translation. Performance is reported on Chinese to English translation of Mandarin Broadcast News
Keywords :
language translation; speech recognition; statistics; ASR word lattices; Mandarin Broadcast News; automatic speech recognition; phrase sequences; phrase-based text translation; speech-to-text translation; statistical phrase-based speech translation; Automatic speech recognition; Broadcasting; Hidden Markov models; Information processing; Lattices; Natural languages; Speech processing; Surface-mount technology; Time to market; Vocabulary;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1660082
