{"total":34,"rows":[{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2205.04382","title":"FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects","created":"2022-05-09","cited_by_count":91,"area":null},{"id":"2211.09325","title":"TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation","created":"2022-11-17","cited_by_count":47,"area":null},{"id":"2110.01500","title":"Factorized Neural Transducer for Efficient Language Model Adaptation","created":"2021-09-27","cited_by_count":32,"area":null},{"id":"2102.07739","title":"Personalization Strategies for End-to-End Speech Recognition Systems","created":"2021-02-15","cited_by_count":26,"area":null},{"id":"2110.02220","title":"Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition","created":"2021-10-05","cited_by_count":25,"area":null},{"id":"2108.06453","title":"Efficient Federated Meta-Learning over Multi-Access Wireless Networks","created":"2021-08-14","cited_by_count":13,"area":null},{"id":"2212.01992","title":"Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models","created":"2022-12-05","cited_by_count":11,"area":null},{"id":"2304.09607","title":"CB-Conformer: Contextual biasing Conformer for biased word recognition","created":"2023-04-19","cited_by_count":11,"area":null},{"id":"2108.00084","title":"The History of Speech Recognition to the Year 2030","created":"2021-07-30","cited_by_count":10,"area":null},{"id":"2202.09003","title":"End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system","created":"2022-02-18","cited_by_count":7,"area":null},{"id":"2206.13240","title":"A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2207.00706","title":"UserLibri: A Dataset for ASR Personalization Using Only Text","created":"2022-07-02","cited_by_count":6,"area":null},{"id":"2106.10259","title":"On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2305.17846","title":"Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation","created":"2023-05-29","cited_by_count":5,"area":null},{"id":"2410.18862","title":"FedSPD: A Soft-clustering Approach for Personalized Decentralized Federated Learning","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2110.11006","title":"Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2304.13149","title":"Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunities","created":"2023-04-25","cited_by_count":4,"area":null},{"id":"2306.02317","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2401.13146","title":"Locality enhanced dynamic biasing and sampling strategies for contextual ASR","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2202.10101","title":"BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search engines","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2309.09524","title":"Improved Factorized Neural Transducer Model For text-only Domain Adaptation","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2310.00141","title":"The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2405.08996","title":"Learning Correspondence for Deformable Objects","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2407.06310","title":"Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2412.10431","title":"CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2302.09723","title":"Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2309.07369","title":"Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation","created":"2023-09-14","cited_by_count":1,"area":null},{"id":"2306.09384","title":"MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.17267","title":"Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2405.08991","title":"Theoretical Analysis for Expectation-Maximization-Based Multi-Model 3D Registration","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2405.16191","title":"Rocket Landing Control with Grid Fins and Path-following using MPC","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2408.10443","title":"Federated Learning of Large ASR Models in the Real World","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2411.17537","title":"Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition","created":"2024-11-26","cited_by_count":0,"area":null}],"next_cursor":null}