System Description: A Highly Interactive Speech-to-Speech Translation System.
Mike DillingerMark SeligmanPublished in: AMTA (2004)
Keyphrases
- highly interactive
- speech recognition
- user friendly
- speech synthesis
- text to speech
- speaker recognition
- speech signal
- noisy environments
- audio visual
- machine translation
- spoken language
- recognition engine
- machine learning
- speech recognizer
- audio stream
- vocal tract
- spontaneous speech
- data sets
- speech processing
- automatic speech recognition
- pattern recognition
- case study
- neural network