{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"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":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"id":"1911.12747","title":"ASR is all you need: cross-modal distillation for lip reading","created":"2019-11-28","cited_by_count":88},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","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":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2001.04758","title":"Deep Audio-Visual Learning: A Survey","created":"2020-01-14","cited_by_count":69},{"id":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"2104.00924","title":"Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning","created":"2021-04-02","cited_by_count":62},{"id":"2005.05592","title":"Discriminative Multi-modality Speech Recognition","created":"2020-05-12","cited_by_count":58},{"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":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"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":"2001.01656","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","created":"2020-01-06","cited_by_count":38},{"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":"2203.15321","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","created":"2022-03-29","cited_by_count":30},{"id":"1812.06589","title":"Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning","created":"2018-12-17","cited_by_count":28},{"id":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24},{"id":"2210.15324","title":"Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning","created":"2022-10-27","cited_by_count":22},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22},{"id":"2110.05267","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","created":"2021-10-11","cited_by_count":18},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18},{"id":"2111.06316","title":"Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport","created":"2021-11-11","cited_by_count":16},{"id":"2203.07996","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","created":"2022-02-24","cited_by_count":12},{"id":"1909.01939","title":"EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks","created":"2019-09-03","cited_by_count":11},{"id":"2302.11989","title":"Metric-oriented Speech Enhancement using Diffusion Probabilistic Model","created":"2023-02-23","cited_by_count":11},{"id":"1711.08010","title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","created":"2017-11-21","cited_by_count":10},{"id":"2110.09890","title":"Multi-Modal Pre-Training for Automated Speech Recognition","created":"2021-10-12","cited_by_count":10},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10},{"id":"2203.14838","title":"Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition","created":"2022-03-28","cited_by_count":10},{"id":"2302.11131","title":"Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation","created":"2023-02-22","cited_by_count":10},{"id":"2304.04974","title":"Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR","created":"2023-04-11","cited_by_count":10},{"id":"2302.11981","title":"Unsupervised Noise adaptation using Data Simulation","created":"2023-02-23","cited_by_count":9},{"id":"1805.02934","title":"Phoneme-to-viseme mappings: the good, the bad, and the ugly","created":"2018-05-08","cited_by_count":7},{"id":"2001.09221","title":"Data Techniques For Online End-to-end Speech Recognition","created":"2020-01-24","cited_by_count":1},{"id":"2205.01751","title":"On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training","created":"2022-05-03","cited_by_count":1}],"next_cursor":null}