Streaming Simultaneous Speech Translation with Augmented Memory Transformer.
Xutai MaYongqiang WangMohammad Javad DoustiPhilipp KoehnJuan Miguel PinoPublished in: ICASSP (2021)
Keyphrases
- speech recognition
- data streams
- fuzzy logic
- speech signal
- memory space
- computing power
- machine translation
- memory requirements
- streaming data
- memory size
- speech synthesis
- limited memory
- noisy environments
- main memory
- memory usage
- endpoint detection
- power system
- hidden markov models
- partial discharge
- recognition engine
- language resources
- real time
- hearing impaired
- text to speech
- parallel corpora
- broadcast news
- spoken language
- automatic speech recognition
- video streaming
- associative memory
- information retrieval