Speech-to-speech translations stutter, but researchers see mellifluous future.
Paul HymanPublished in: Commun. ACM (2014)
Keyphrases
- speech recognition
- speech signal
- audio visual
- automatic speech recognition
- broadcast news
- recognition engine
- text to speech
- data mining
- endpoint detection
- spoken language
- noisy environments
- hidden markov models
- data sets
- emotional state
- computational intelligence
- linear prediction
- long term
- speaker recognition
- computer science
- speech synthesis
- spontaneous speech
- machine learning