The Impact of ASR on Speech-to-Speech Translation Performance.
Ruhi SarikayaBowen ZhouDaniel PoveyMohamed AfifyYuqing GaoPublished in: ICASSP (4) (2007)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- spontaneous speech
- audio visual
- hidden markov models
- word error rate
- text to speech
- speech synthesis
- database
- noisy environments
- broadcast news
- vocal tract
- automatic speech recognition systems
- endpoint detection
- conversational speech
- machine translation
- speech processing
- speech recognizer
- spoken language
- speech corpus
- audio stream
- genetic algorithm
- multi lingual
- human machine interaction
- dialogue system
- recognition engine
- hearing impaired
- neural network