On the selection of meaningful speech parameters used by a pathologic/non pathologic voice register classifier.
Juan Ignacio Godino-LlorenteSantiago Aguilera-NavarroCarlos Hernández-EspinosaMercedes Fernández-RedondoPedro Gómez VildaPublished in: EUROSPEECH (1999)
Keyphrases
- text to speech
- fine tuning
- maximum likelihood
- decision trees
- feature selection
- emotion recognition
- selection criterion
- classification rate
- speech recognition
- input data
- linear classifiers
- feature space
- learning algorithm
- speech synthesis
- parameter values
- feature set
- training data
- lexical features
- speech sounds
- voice activity detection