Using multiple recognition hypotheses to improve speech translation.
Ruiqiang ZhangGen-ichiro KikuiHirofumi YamamotoPublished in: IWSLT (2005)
Keyphrases
- recognition engine
- recognition rate
- multiple hypotheses
- object recognition
- continuous speech recognition
- spoken language
- machine translation
- recognition accuracy
- feature extraction
- audio visual
- cross language information retrieval
- automatic recognition
- character recognition
- automatic speech recognition systems
- recognition process
- gait recognition
- visual recognition
- recognition algorithm
- speech recognition
- multi modal
- information extraction
- pattern recognition
- video sequences