Generalized variable parameter HMMs based acoustic-to-articulatory inversion.
Xurong XieXunying LiuLan WangRongfeng SuPublished in: INTERSPEECH (2015)
Keyphrases
- speech recognition
- hidden markov models
- multi stream
- acoustic features
- speaker independent
- speech recognition systems
- parameter space
- acoustic models
- parameter values
- speech signal
- parameter settings
- image reconstruction
- automatic speech recognition
- optimal parameters
- noisy environments
- discriminative training
- source localization
- underwater acoustic
- dynamic programming
- pattern recognition