Target-Speaker Voice Activity Detection Via Sequence-to-Sequence Prediction.
Ming ChengWeiqing WangYucong ZhangXiaoyi QinMing LiPublished in: ICASSP (2023)
Keyphrases
- sequence prediction
- voice activity detection
- markov models
- decision theory
- speech recognition
- reinforcement learning
- automatic speech recognition
- noisy environments
- structured prediction
- artificial intelligence
- supervised learning
- learning algorithm
- computer vision
- feature selection
- active learning
- probability distribution