Superhuman speech by 2010: an interview with Jennifer Lai.
Paula BachPublished in: ACM Crossroads (2007)
Keyphrases
- speech recognition
- audio visual
- speech signal
- case study
- endpoint detection
- text to speech
- language acquisition
- data collection
- speech synthesis
- audio stream
- multi stream
- emotion recognition
- spoken language
- real time
- recognition engine
- neural network
- speaker identification
- broadcast news
- information systems
- dialogue system
- feature extraction
- video sequences
- hidden markov models
- computational model
- visual features