|
- nullDCTCN:Deep Complex Temporal Convolutional Network for Long Time Speech Enhancement
- nullAdaptive Hierarchical Pooling for Weakly-supervised Sound Event Detection
- nullWeighted contrastive learning using pseudo labels for facial expression recognition
- nullOn synthesis for supervised monaural speech separation in time domain
- nullAn efficient speech emotion recognition based on a dual-stream CNN-transformer fusion network
- nullClustering Driven Multi-Hop Graph Attention Network for Speaker Diarization
- nullDual-path transformer network: Direct context-aware modeling for end-to-end monaural speech separation
- nullWeakly Supervised Sentiment-Specific Region Discovery for VSA
- nullJoint-Former: Jointly Regularized and Locally Down-sampled Conformer for Semi-supervised Sound Event Detection
- nullPhase sensitive masking-based single channel speech enhancement using conditional generative adversarial network