{"total":47,"rows":[{"id":"2103.14023","title":"AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting","created":"2021-03-25","cited_by_count":331,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2105.00982","title":"On the limit of English conversational speech recognition","created":"2021-05-03","cited_by_count":30,"area":null},{"id":"2201.05562","title":"Investigation of Data Augmentation Techniques for Disordered Speech Recognition","created":"2022-01-14","cited_by_count":27,"area":null},{"id":"2102.10801","title":"Neural Delay Differential Equations","created":"2021-02-22","cited_by_count":26,"area":null},{"id":"2206.08671","title":"FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18,"area":null},{"id":"2201.05845","title":"Recent Progress in the CUHK Dysarthric Speech Recognition System","created":"2022-01-15","cited_by_count":17,"area":null},{"id":"2102.06474","title":"Transformer Language Models with LSTM-based Cross-utterance Information Representation","created":"2021-02-12","cited_by_count":15,"area":null},{"id":"2408.16287","title":"Measuring the Accuracy of Automatic Speech Recognition Solutions","created":"2024-08-29","cited_by_count":15,"area":null},{"id":"2104.11070","title":"Adapting Long Context NLM for ASR Rescoring in Conversational Agents","created":"2021-04-21","cited_by_count":12,"area":null},{"id":"2110.03841","title":"Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition","created":"2021-10-08","cited_by_count":10,"area":null},{"id":"2312.11522","title":"Assessing SATNet's Ability to Solve the Symbol Grounding Problem","created":"2023-12-13","cited_by_count":10,"area":null},{"id":"2103.15975","title":"Platform for Situated Intelligence","created":"2021-03-29","cited_by_count":9,"area":null},{"id":"2104.04298","title":"On Architectures and Training for Raw Waveform Feature Extraction in ASR","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2106.09532","title":"ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modeling","created":"2021-06-15","cited_by_count":7,"area":null},{"id":"2202.12603","title":"Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR","created":"2022-02-25","cited_by_count":7,"area":null},{"id":"2305.13408","title":"Modular Domain Adaptation for Conformer-Based Streaming ASR","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2104.00120","title":"Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2111.05496","title":"ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees","created":"2021-11-10","cited_by_count":6,"area":null},{"id":"2206.09843","title":"Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification","created":"2022-06-20","cited_by_count":6,"area":null},{"id":"2210.05840","title":"LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2305.13794","title":"Personalized Predictive ASR for Latency Reduction in Voice Assistants","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2204.00145","title":"MyMove: Facilitating Older Adults to Collect In-Situ Activity Labels on a Smartwatch with Speech","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2107.06785","title":"Large-Scale News Classification using BERT Language Model: Spark NLP Approach","created":"2021-07-14","cited_by_count":3,"area":null},{"id":"2101.09788","title":"Evaluating Models of Robust Word Recognition with Serial Reproduction","created":"2021-01-24","cited_by_count":2,"area":null},{"id":"2102.11114","title":"Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model","created":"2021-02-22","cited_by_count":2,"area":null},{"id":"2105.03409","title":"A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect","created":"2021-05-07","cited_by_count":2,"area":null},{"id":"2111.03993","title":"Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2301.06475","title":"Using Kaldi for Automatic Speech Recognition of Conversational Austrian German","created":"2023-01-16","cited_by_count":2,"area":null},{"id":"2306.16903","title":"Leveraging Cross-Utterance Context For ASR Decoding","created":"2023-06-29","cited_by_count":1,"area":null},{"id":"2410.15620","title":"Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2510.21048","title":"xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2101.04773","title":"Practical Speech Re-use Prevention in Voice-driven Services","created":"2021-01-12","cited_by_count":0,"area":null},{"id":"2103.15294","title":"\"Weak AI\" is Likely to Never Become \"Strong AI\", So What is its Greatest Value for us?","created":"2021-03-29","cited_by_count":0,"area":null},{"id":"2106.01730","title":"Drivers' Manoeuvre Modelling and Prediction for Safe HRI","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2110.03999","title":"Graphs as Tools to Improve Deep Learning Methods","created":"2021-10-08","cited_by_count":0,"area":null},{"id":"2111.02784","title":"On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamics","created":"2021-11-03","cited_by_count":0,"area":null},{"id":"2112.10108","title":"Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition","created":"2021-12-19","cited_by_count":0,"area":null},{"id":"2204.13678","title":"Unified Simulation, Perception, and Generation of Human Behavior","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2304.05310","title":"Neural Delay Differential Equations: System Reconstruction and Image Classification","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2312.12764","title":"Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2404.17394","title":"Child Speech Recognition in Human-Robot Interaction: Problem Solved?","created":"2024-04-26","cited_by_count":0,"area":null},{"id":"2504.03887","title":"Accurate GPU Memory Prediction for Deep Learning Jobs through Dynamic Analysis","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2601.15209","title":"Deaf and Hard of Hearing Access to Intelligent Personal Assistants: Comparison of Voice-Based Options with an LLM-Powered Touch Interface","created":"2026-01-21","cited_by_count":0,"area":null}],"next_cursor":null}