{"total":27,"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":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2102.03216","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","created":"2021-02-05","cited_by_count":96,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2203.06801","title":"MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks","created":"2022-03-14","cited_by_count":34,"area":null},{"id":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"area":null},{"id":"2101.01896","title":"Taxonomy Completion via Triplet Matching Network","created":"2021-01-06","cited_by_count":21,"area":null},{"id":"2308.08942","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","created":"2023-08-17","cited_by_count":20,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2110.04109","title":"Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2311.15571","title":"Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples","created":"2023-11-27","cited_by_count":11,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2312.15190","title":"SAIC: Integration of Speech Anonymization and Identity Classification","created":"2023-12-23","cited_by_count":7,"area":null},{"id":"2103.00771","title":"Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning","created":"2021-03-01","cited_by_count":6,"area":null},{"id":"2204.00176","title":"Better Intermediates Improve CTC Inference","created":"2022-04-01","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":"2205.12462","title":"Improving CTC-based ASR Models with Gated Interlayer Collaboration","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2112.06721","title":"PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition","created":"2021-12-13","cited_by_count":3,"area":null},{"id":"2311.14835","title":"Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2401.16520","title":"MT-HCCAR: Multi-Task Deep Learning with Hierarchical Classification and Attention-based Regression for Cloud Property Retrieval","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2510.18938","title":"StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2103.03862","title":"Harnessing Geometric Constraints from Emotion Labels to improve Face Verification","created":"2021-03-05","cited_by_count":0,"area":null},{"id":"2201.01806","title":"Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2204.00175","title":"Alternate Intermediate Conditioning with Syllable-level and Character-level Targets for Japanese ASR","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2205.11998","title":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2402.15594","title":"Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR","created":"2024-02-23","cited_by_count":0,"area":null}],"next_cursor":null}