Transformer-based Cascaded Multimodal Speech Translation.
Zixiu WuOzan CaglayanJulia IveJosiah WangLucia SpeciaPublished in: IWSLT (2019)
Keyphrases
- audio visual
- multimodal interfaces
- multi stream
- speech recognition
- machine translation
- fuzzy logic
- multimodal interaction
- multi modal
- human computer interaction
- face detection
- automatic speech recognition
- multimodal information
- speech synthesis
- fault diagnosis
- text to speech
- spoken language
- broadcast news
- spoken dialogue systems
- learning mechanism
- expert systems
- query translation
- visual information
- incipient fault