Speaker Adaptation Based on PARAFAC2 of Transformation Matrices for Continuous Speech Recognition.
Yongwon JeongSangjun LimYoung Kuk KimHyung Soon KimPublished in: IEICE Trans. Inf. Syst. (2013)
Keyphrases
- continuous speech recognition
- speaker adaptation
- speech recognition
- maximum likelihood
- singular value decomposition
- automatic speech recognition
- high order
- speech recognizer
- speaker independent
- speaker dependent
- singular values
- tensor decomposition
- feature selection
- hidden markov models
- speaker identification
- singular vectors