Automatic speaker age and gender recognition using acoustic and prosodic level information fusion.
Ming LiKyu Jeong HanShrikanth S. NarayananPublished in: Comput. Speech Lang. (2013)
Keyphrases
- information fusion
- prosodic features
- data fusion
- speech recognition
- fusion algorithm
- speaker verification
- soft computing
- multi source
- information gathering
- fusion method
- text to speech
- fusion model
- situation awareness
- speech synthesis
- emotion recognition
- data mining
- age groups
- pattern recognition
- acoustic models
- decision level
- acoustic features
- multi sensor