Deriving articulatory representations of speech.
Hywel B. RichardsJohn S. MasonMelvyn J. HuntJohn S. BridlePublished in: EUROSPEECH (1995)
Keyphrases
- speech recognition
- vocal tract
- speech signal
- speech synthesis
- multi stream
- acoustic features
- text to speech
- automatic speech recognition
- multiple representations
- formant frequencies
- hearing impaired
- endpoint detection
- distributed representations
- speech processing
- speaker recognition
- data sets
- speaker identification
- emotion recognition
- audio visual
- language model
- hidden markov models
- pattern recognition
- neural network