Training Simultaneous Speech Translation with Robust and Random Wait-k-Tokens Strategy.
Linlin ZhangKai FanJiajun BuZhongqiang HuangPublished in: EMNLP (2023)
Keyphrases
- hearing impaired
- test set
- simultaneous optimization
- training set
- speech recognition
- pattern recognition
- evolutionary algorithm
- audio visual
- training algorithm
- machine translation
- computationally efficient
- training phase
- robust estimation
- training examples
- genetic algorithm
- multi modal
- online learning
- active learning
- natural language
- support vector
- face recognition
- feature selection