Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code.
Ossama Abdel-HamidHui JiangPublished in: ICASSP (2013)
Keyphrases
- speech recognition
- speaker adaptation
- hidden markov models
- speaker independent
- automatic speech recognition
- speaker dependent
- neural network
- speech synthesis
- pattern recognition
- language model
- probabilistic model
- speech signal
- speech recognizer
- speaker identification
- prior knowledge
- noisy environments
- maximum likelihood
- support vector
- feature selection