Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits.
Qingjian LinLin YangXuyang WangLuyuan XieChen JiaJunjie WangPublished in: CoRR (2021)
Keyphrases
- language acquisition
- supervised learning
- speech recognition
- learning algorithm
- learning process
- online learning
- speech synthesis
- speaker recognition
- reinforcement learning
- hearing impaired
- automatic speech recognition
- active learning
- speech signal
- learning systems
- spoken language
- learning tasks
- learning problems
- mobile learning
- learning mechanism
- feedforward neural networks
- learning speed
- prior knowledge
- pattern recognition