{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"1910.11006","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","created":"2019-10-24","cited_by_count":218},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129},{"id":"2211.01367","title":"Two-Stream Network for Sign Language Recognition and Translation","created":"2022-11-02","cited_by_count":123},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"id":"2307.14768","title":"Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining","created":"2023-07-27","cited_by_count":105},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"id":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77},{"id":"2306.15162","title":"YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus","created":"2023-06-27","cited_by_count":75},{"id":"1911.04890","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","created":"2019-11-08","cited_by_count":74},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63},{"id":"1807.05162","title":"Large-Scale Visual Speech Recognition","created":"2018-07-13","cited_by_count":57},{"id":"2405.04164","title":"Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation","created":"2024-05-07","cited_by_count":57},{"id":"2501.15187","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","created":"2025-01-25","cited_by_count":56},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47},{"id":"2402.09611","title":"Towards Privacy-Aware Sign Language Translation at Scale","created":"2024-02-14","cited_by_count":44},{"id":"2409.12319","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","created":"2024-09-18","cited_by_count":42},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37},{"id":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31},{"id":"2405.14312","title":"Improving Gloss-free Sign Language Translation by Reducing Representation Density","created":"2024-05-23","cited_by_count":31},{"id":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30},{"id":"2501.09754","title":"Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues","created":"2025-01-16","cited_by_count":26},{"id":"2403.12556","title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","created":"2024-03-19","cited_by_count":24},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21},{"id":"2404.02098","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","created":"2024-04-02","cited_by_count":21},{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19},{"id":"1701.05847","title":"End-To-End Visual Speech Recognition With LSTMs","created":"2017-01-20","cited_by_count":16},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16},{"id":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","cited_by_count":15},{"id":"2309.08535","title":"Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper","created":"2023-09-15","cited_by_count":13},{"id":"2505.15438","title":"Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation","created":"2025-05-21","cited_by_count":12},{"id":"2303.11771","title":"Self-Sufficient Framework for Continuous Sign Language Recognition","created":"2023-03-21","cited_by_count":11},{"id":"2211.08954","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","created":"2022-11-16","cited_by_count":10},{"id":"2309.12304","title":"SlowFast Network for Continuous Sign Language Recognition","created":"2023-09-21","cited_by_count":10},{"id":"2211.00448","title":"Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition","created":"2022-11-01","cited_by_count":8},{"id":"2407.11855","title":"Scaling Sign Language Translation","created":"2024-07-16","cited_by_count":8},{"id":"2503.03287","title":"Deep Understanding of Sign Language for Sign to Subtitle Alignment","created":"2025-03-05","cited_by_count":6}],"next_cursor":null}