An Analysis of Machine Translation and Speech Synthesis in Speech-To-Speech Translation System

Conference object, Contribution for newspaper or weekly magazine English OPEN
Hashimoto, K.; Yamagishi, J.; Byrne, W.; King, S.; Tokuda, K.;
(2011)
  • Publisher: Institute of Electrical and Electronics Engineers
  • Journal: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2011.5,108-5,111 (issn: 1520-6149)
  • Publisher copyright policies & self-archiving
  • Related identifiers: doi: 10.1109/ICASSP.2011.5947506
  • Subject: Hidden Markov models | speech recognition | speechto-speech translation | Speech synthesis | Correlation | Speech | Training data | machine translation | Natural languages | speech-to-speech translation system | subjective evaluation

This paper provides an analysis of the impacts of machine translation and speech synthesis on speech-to-speech translation systems. The speech-to-speech translation system consists of three components: speech recognition, machine translation and speech synthesis. Many t... View more
Share - Bookmark