Deriving articulatory representations from speech with various excitation modes.
Hywel B. RichardsJohn S. MasonMelvyn J. HuntJohn S. BridlePublished in: ICSLP (1996)
Keyphrases
- speech recognition
- vocal tract
- speech signal
- speech synthesis
- multi stream
- automatic speech recognition
- speaker identification
- acoustic features
- speech processing
- speech recognizer
- higher level
- text to speech
- multiple representations
- hidden markov models
- pattern recognition
- face recognition
- information retrieval
- lexical features
- endpoint detection
- representation scheme
- linear prediction
- emotion recognition
- database
- symbolic representation
- natural language processing
- machine learning
- data sets
- real time