Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
Luisa BentivogliMauro CettoloMarco GaidoAlina KarakantaAlberto MartinelliMatteo NegriMarco TurchiPublished in: ACL/IJCNLP (1) (2021)
Keyphrases
- speech recognition
- machine translation
- statistically significant
- speech synthesis
- age groups
- speech signal
- neural network
- endpoint detection
- speaker verification
- broadcast news
- cross language information retrieval
- human computer interaction
- pattern recognition
- data sets
- language acquisition
- emotion recognition
- language resources
- recognition engine