Standalone training of context-dependent deep neural network acoustic models.
Chao ZhangPhilip C. WoodlandPublished in: ICASSP (2014)
Keyphrases
- context dependent
- acoustic models
- neural network
- training process
- speech recognition
- hidden markov models
- discriminative training
- speech recognizer
- pattern recognition
- automatic speech recognition
- low level
- natural language
- supervised learning
- broadcast news
- training set
- high level
- deep learning
- information retrieval systems
- n gram
- video data
- feature vectors
- training data
- data mining