Personalising Speech-To-Speech Translation in the EMIME Project.
Mikko KurimoWilliam ByrneJohn DinesPhilip N. GarnerMatthew GibsonYong GuanTeemu HirsimäkiReima KarhilaSimon KingHui LiangKeiichiro OuraLakshmi SaheerMatt ShannonSayaka ShiotaJilei TianPublished in: ACL (System Demonstrations) (2010)
Keyphrases
- speech recognition
- broadcast news
- automatic speech recognition
- speech synthesis
- spoken language
- endpoint detection
- speech signal
- noisy environments
- speaker recognition
- case study
- audio stream
- recognition engine
- speech recognizer
- multimodal interfaces
- audio visual
- natural language
- spoken dialogue systems
- speaker identification
- speech processing
- target language
- machine translation
- information extraction
- finite state transducers
- data sets
- hearing impaired