Techniques

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training ICLR 2022 The ZevoMOS entry to VoiceMOS Challenge 2022 Interspeech 2022 Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network Interspeech 2022 Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation Interspeech 2022 To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding IJCAI 2022 TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers NeurIPS 2022 Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems Interspeech 2022 Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access EMNLP 2022 To update or not to update? Neurons at equilibrium in deep models NeurIPS 2022 Toward Efficient Robust Training against Union of ℓ_p Threat Models NeurIPS 2022 Towards an Effective Orthogonal Dictionary Convolution Strategy AAAI 2022 Towards Better Document-level Relation Extraction via Iterative Inference EMNLP 2022 Towards Efficient and Scalable Sharpness-Aware Minimization CVPR 2022 Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Swithboard Corpus Interspeech 2022 Towards high-fidelity singing voice conversion with acoustic reference and contrastive predictive coding Interspeech 2022 Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information Interspeech 2022 Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework EMNLP 2022 Towards Robust Vision Transformer CVPR 2022 Towards Theoretically Inspired Neural Initialization Optimization NeurIPS 2022 Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models NAACL 2022 Towards Weakly-Supervised Text Spotting Using a Multi-Task Transformer CVPR 2022 Toward Understanding Convolutional Neural Networks from Volterra Convolution Perspective JMLR 2022 TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract) AAAI 2022 Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization ICLR 2022 Training-Free Transformer Architecture Search CVPR 2022