Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition.
Shaofei XueHui JiangLi-Rong DaiQingfeng LiuPublished in: J. Signal Process. Syst. (2016)
Keyphrases
- speech recognition
- hidden markov models
- singular value decomposition
- speaker adaptation
- speech recognizer
- automatic speech recognition
- pattern recognition
- language model
- speech signal
- neural network
- probabilistic model
- noisy environments
- speaker dependent
- em algorithm
- least squares
- speaker identification
- speech synthesis