Multi-task deep neural network acoustic models with model adaptation using discriminative speaker identity for whisper recognition.
Jingjie LiIan McLoughlinCong LiuShaofei XueSi WeiPublished in: ICASSP (2015)
Keyphrases
- multi task
- acoustic models
- speaker independent
- speech recognition
- neural network
- multi task learning
- discriminative training
- hidden markov models
- pattern recognition
- learning tasks
- feature selection
- automatic speech recognition
- feature extraction
- learning problems
- speaker identification
- speech recognizer
- multi class
- broadcast news
- speech recognition systems
- training process
- transfer learning
- digit recognition
- information gain
- language model
- support vector
- machine learning
- prior knowledge
- support vector machine
- unsupervised learning
- multi modal