An investigation of dependencies between frequency components and speaker characteristics based on phoneme mean F-ratio contribution.
Songgun HyonHongcui WangJianguo WeiJianwu DangPublished in: APSIPA (2012)
Keyphrases
- speech recognition
- automatic speech recognition
- prosodic features
- speaker dependent
- hidden markov models
- automatic speech recognition systems
- real time
- genetic algorithm
- artificial intelligence
- case study
- bayesian networks
- pattern recognition
- low level
- integrity constraints
- speaker identification
- speaker verification