Yanhua Long

automatic speech recognition (4) speech enhancement (3) attention mechanism (2) transformer architecture (1) multi-task learning (1) self-attention mechanism (1) semi-supervised learning (1) sound separation (1) speech recognition (1) signal-to-noise ratio (1) low-resource learning (1) transfer learning (1) semi-supervised training (1) connectionist temporal classification (1) representation learning (1) real-time processing (1) active learning (1) multi-objective learning (1) synthetic speech detection (1) unsupervised learning (1)