The JHU/KyotoU Speech Translation System for IWSLT 2018.
Hirofumi InagumaXuan ZhangZhiqi WangAdithya RenduchintalaShinji WatanabeKevin DuhPublished in: IWSLT (2018)
Keyphrases
- speech recognition
- machine translation
- speech signal
- audio visual
- endpoint detection
- cross language information retrieval
- speech processing
- broadcast news
- automatic speech recognition systems
- text to speech synthesis
- speech synthesis
- multi lingual
- emotion recognition
- hearing impaired
- vocal tract
- multimodal interfaces
- speaker recognition
- spoken language
- genetic algorithm
- noisy environments
- dialogue system
- automatic speech recognition
- query translation
- cross language
- artificial intelligence