{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"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":"2012.07657","title":"Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection","created":"2020-12-14","cited_by_count":287},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1805.04699","title":"TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation","created":"2018-05-12","cited_by_count":226},{"id":"1905.00641","title":"RetinaFace: Single-stage Dense Face Localisation in the Wild","created":"2019-05-02","cited_by_count":165},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"id":"2011.12998","title":"VoxLingua107: a Dataset for Spoken Language Recognition","created":"2020-11-25","cited_by_count":122},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101},{"id":"1905.04226","title":"Language Modeling with Deep Transformers","created":"2019-05-10","cited_by_count":96},{"id":"2102.03216","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","created":"2021-02-05","cited_by_count":96},{"id":"1911.12747","title":"ASR is all you need: cross-modal distillation for lip reading","created":"2019-11-28","cited_by_count":88},{"id":"1904.03416","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","created":"2019-04-06","cited_by_count":87},{"id":"1611.01599","title":"LipNet: End-to-End Sentence-level Lipreading","created":"2016-11-05","cited_by_count":80},{"id":"2007.01216","title":"Spot the conversation: speaker diarisation in the wild","created":"2020-07-02","cited_by_count":79},{"id":"1911.04890","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","created":"2019-11-08","cited_by_count":74},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"1703.04105","title":"Combining Residual Networks with LSTMs for Lipreading","created":"2017-03-12","cited_by_count":68},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"1807.05162","title":"Large-Scale Visual Speech Recognition","created":"2018-07-13","cited_by_count":57},{"id":"1701.00495","title":"Vid2speech: Speech Reconstruction from Silent Video","created":"2017-01-02","cited_by_count":53},{"id":"2007.06504","title":"Towards Practical Lipreading with Distilled and Efficient Models","created":"2020-07-13","cited_by_count":45},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44},{"id":"1911.11502","title":"Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers","created":"2019-11-26","cited_by_count":41},{"id":"2001.01656","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","created":"2020-01-06","cited_by_count":38},{"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":"1704.01631","title":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","created":"2017-04-05","cited_by_count":29},{"id":"2011.03109","title":"Improving RNN Transducer Based ASR with Auxiliary Tasks","created":"2020-11-05","cited_by_count":27},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27},{"id":"1908.04917","title":"A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading","created":"2019-08-14","cited_by_count":25},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21},{"id":"2002.00551","title":"End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection","created":"2020-02-03","cited_by_count":20},{"id":"2004.02541","title":"Vocoder-Based Speech Synthesis from Silent Videos","created":"2020-04-06","cited_by_count":20},{"id":"1911.06095","title":"Towards Pose-invariant Lip-Reading","created":"2019-11-14","cited_by_count":12},{"id":"2007.04134","title":"Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision","created":"2020-07-08","cited_by_count":9},{"id":"2004.08250","title":"How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition","created":"2020-04-17","cited_by_count":8},{"id":"1708.01565","title":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","created":"2017-08-04","cited_by_count":7},{"id":"1709.00443","title":"End-to-End Multi-View Lipreading","created":"2017-09-01","cited_by_count":7},{"id":"1802.06399","title":"Visual-Only Recognition of Normal, Whispered and Silent Speech","created":"2018-02-18","cited_by_count":7},{"id":"1906.02112","title":"Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition","created":"2019-06-05","cited_by_count":6},{"id":"1710.01073","title":"Resolution limits on visual speech recognition","created":"2017-10-03","cited_by_count":5},{"id":"2109.09536","title":"Audio-Visual Speech Recognition is Worth 32$\\times$32$\\times$8 Voxels","created":"2021-09-20","cited_by_count":5},{"id":"1905.12605","title":"Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect","created":"2019-05-29","cited_by_count":4},{"id":"2104.09482","title":"Fusing information streams in end-to-end audio-visual speech recognition","created":"2021-04-19","cited_by_count":4}],"next_cursor":null}