Ensemble speaker modeling using speaker adaptive training deep neural network for speaker adaptation.
Sheng LiXugang LuYuya AkitaTatsuya KawaharaPublished in: INTERSPEECH (2015)
Keyphrases
- speaker adaptation
- neural network
- speech recognition
- speaker dependent
- automatic speech recognition
- maximum likelihood
- speaker independent
- training set
- audio visual
- training process
- multi layer perceptron
- speaker identification
- artificial neural networks
- multi modal
- hidden markov models
- speech signal
- pattern recognition
- speaker recognition
- vocal tract
- language model
- speaker verification
- speaker diarization
- bayesian networks
- training data