The Status of Variable Phonetic Output in Early Speech.
Elinor PayneEftychia EftychiouBrechtje PostLluïsa AstrucPilar PrietoMaría VanrellPublished in: ICPhS (2011)
Keyphrases
- speech recognition
- spoken term detection
- speech sounds
- automatic speech recognition
- speech synthesis
- speech recognizer
- spoken document retrieval
- speaker independent
- speech signal
- pattern recognition
- endpoint detection
- language model
- emotional speech
- recognition engine
- real time
- acoustic models
- database
- speaker identification
- speech recognition systems
- emotion recognition
- input variables
- input data
- information retrieval
- neural network