ESPnet-ST: All-in-One Speech Translation Toolkit.
Hirofumi InagumaShun KiyonoKevin DuhShigeki KaritaNelson Enrique Yalta SoplinTomoki HayashiShinji WatanabePublished in: CoRR (2020)
Keyphrases
- speech recognition
- speech synthesis
- speech signal
- machine translation
- audio visual
- text to speech
- endpoint detection
- recognition engine
- speech quality
- finite state transducers
- vocal tract
- speech processing
- query translation
- speaker recognition
- spoken language
- automatic speech recognition
- speaker verification
- statistical machine translation
- real time
- cross language information retrieval
- cross language
- document collections
- human computer interaction
- language model
- image sequences
- machine learning