{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879},{"id":"2106.01357","title":"Diffusion Schr\\\"odinger Bridge with Applications to Score-Based Generative Modeling","created":"2021-06-01","cited_by_count":602},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1308.0215","title":"A survey of the Schr\\\"odinger problem and some of its connections with optimal transport","created":"2013-08-01","cited_by_count":292},{"id":"1705.08848","title":"Joint Distribution Optimal Transportation for Domain Adaptation","created":"2017-05-24","cited_by_count":282},{"id":"2102.12086","title":"Modern Koopman Theory for Dynamical Systems","created":"2021-02-24","cited_by_count":276},{"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":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"1908.10962","title":"Optimal transport mapping via input convex neural networks","created":"2019-08-28","cited_by_count":206},{"id":"1901.05335","title":"A review of domain adaptation without target labels","created":"2019-01-16","cited_by_count":156},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138},{"id":"2201.12220","title":"Neural Optimal Transport","created":"2022-01-28","cited_by_count":126},{"id":"1412.4430","title":"On the relation between optimal transport and Schr\\\"odinger bridges: A stochastic control viewpoint","created":"2014-12-15","cited_by_count":99},{"id":"2106.01954","title":"Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark","created":"2021-06-03","cited_by_count":96},{"id":"1811.02834","title":"Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties","created":"2018-11-07","cited_by_count":93},{"id":"1710.06276","title":"Smooth and Sparse Optimal Transport","created":"2017-10-17","cited_by_count":83},{"id":"2403.13117","title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","created":"2024-03-19","cited_by_count":78},{"id":"2103.04737","title":"Low-Rank Sinkhorn Factorization","created":"2021-03-08","cited_by_count":67},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66},{"id":"2007.03511","title":"Estimating Generalization under Distribution Shifts via Domain-Invariant Representations","created":"2020-07-06","cited_by_count":56},{"id":"2211.08775","title":"Unbalanced Optimal Transport, from Theory to Numerics","created":"2022-11-16","cited_by_count":46},{"id":"2107.13469","title":"Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate","created":"2021-07-28","cited_by_count":43},{"id":"2201.12806","title":"Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection","created":"2022-01-30","cited_by_count":39},{"id":"1607.05816","title":"Scaling Algorithms for Unbalanced Transport Problems","created":"2016-07-20","cited_by_count":36},{"id":"2506.02070","title":"An Introduction to Flow Matching and Diffusion Models","created":"2025-06-02","cited_by_count":35},{"id":"1901.06283","title":"Improving Sequence-to-Sequence Learning via Optimal Transport","created":"2019-01-18","cited_by_count":33},{"id":"2004.15003","title":"Word Rotator's Distance","created":"2020-04-30","cited_by_count":32},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31},{"id":"1705.10874","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","created":"2017-05-30","cited_by_count":30},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27},{"id":"2404.13914","title":"A Survey on Speech Deepfake Detection","created":"2024-04-22","cited_by_count":27},{"id":"2301.11716","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","created":"2023-01-27","cited_by_count":25},{"id":"2305.14635","title":"CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation","created":"2023-05-24","cited_by_count":22},{"id":"2201.10103","title":"Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models","created":"2022-01-25","cited_by_count":21},{"id":"1306.3203","title":"Bregman Alternating Direction Method of Multipliers","created":"2013-06-13","cited_by_count":19},{"id":"2202.07894","title":"Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers","created":"2022-02-16","cited_by_count":19},{"id":"2111.06316","title":"Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport","created":"2021-11-11","cited_by_count":16},{"id":"2202.03618","title":"On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error","created":"2022-02-08","cited_by_count":16},{"id":"2203.03582","title":"Improving CTC-based speech recognition via knowledge transferring from pre-trained language models","created":"2022-02-22","cited_by_count":14},{"id":"2104.04805","title":"Non-autoregressive Transformer-based End-to-end ASR using BERT","created":"2021-04-10","cited_by_count":13},{"id":"2210.06244","title":"A context-aware knowledge transferring strategy for CTC-based ASR","created":"2022-10-12","cited_by_count":12},{"id":"2110.12138","title":"Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding","created":"2021-10-23","cited_by_count":11},{"id":"2301.13003","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","created":"2023-01-30","cited_by_count":11},{"id":"2211.00792","title":"BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder","created":"2022-11-02","cited_by_count":8},{"id":"2206.12638","title":"Distilling a Pretrained Language Model to a Multilingual ASR Model","created":"2022-06-25","cited_by_count":7},{"id":"2209.02030","title":"Distilling the Knowledge of BERT for CTC-based ASR","created":"2022-09-05","cited_by_count":6},{"id":"2306.04116","title":"Unbalanced Optimal Transport for Unbalanced Word Alignment","created":"2023-06-07","cited_by_count":6},{"id":"2309.13650","title":"Cross-modal Alignment with Optimal Transport for CTC-based ASR","created":"2023-09-24","cited_by_count":6},{"id":"2012.13152","title":"Unsupervised neural adaptation model based on optimal transport for spoken language identification","created":"2020-12-24","cited_by_count":4},{"id":"2309.16093","title":"Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR","created":"2023-09-28","cited_by_count":4},{"id":"2409.02239","title":"Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR","created":"2024-09-03","cited_by_count":3},{"id":"2501.13375","title":"Bridging The Multi-Modality Gaps of Audio, Visual and Linguistic for Speech Enhancement","created":"2025-01-23","cited_by_count":3},{"id":"2503.07078","title":"Linguistic Knowledge Transfer Learning for Speech Enhancement","created":"2025-03-10","cited_by_count":3},{"id":"1609.04767","title":"Transport-based analysis, modeling, and learning from signal and data distributions","created":"2016-09-15","cited_by_count":1},{"id":"2505.13079","title":"Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR","created":"2025-05-19","cited_by_count":1}],"next_cursor":null}