Multi-Task Multi-Network Joint-Learning of Deep Residual Networks and Cycle-Consistency Generative Adversarial Networks for Robust Speech Recognition.
Shengkui ZhaoChongjia NiRong TongBin MaPublished in: INTERSPEECH (2019)
Keyphrases
- speech recognition
- multi task
- network structure
- learning tasks
- multi task learning
- learning problems
- multiple tasks
- learning algorithm
- language model
- hidden markov models
- learning process
- noisy environments
- pattern recognition
- reinforcement learning
- machine learning
- speech synthesis
- multi class
- prior knowledge
- gaussian processes
- e learning
- automatic speech recognition