Speaker cluster-based speaker adaptive training for deep neural network acoustic modeling.
Wei ChuRuxin ChenPublished in: ICASSP (2016)
Keyphrases
- neural network
- acoustic models
- speech recognition
- speaker verification
- prosodic features
- training algorithm
- training process
- speaker recognition
- acoustic features
- automatic speech recognition
- hidden markov models
- speaker identification
- speech recognizer
- audio visual
- feed forward neural networks
- multi layer perceptron
- neural network model
- training phase
- training set
- test set
- pattern recognition
- training patterns
- neural fuzzy
- automatic transcription
- speech sounds
- back propagation
- fuzzy logic
- probabilistic neural network
- feedforward neural networks
- speech signal
- recurrent networks
- gaussian mixture model
- speaker diarization
- visual speech
- mel frequency cepstral coefficients
- language model
- supervised learning
- artificial neural networks
- synthesized speech
- train a neural network