{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"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":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"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":"2003.03773","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","created":"2020-03-08","cited_by_count":222},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"2010.10504","title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","created":"2020-10-20","cited_by_count":187},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151},{"id":"2005.09629","title":"Improved Noisy Student Training for Automatic Speech Recognition","created":"2020-05-19","cited_by_count":141},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"2010.13956","title":"Recent Developments on ESPnet Toolkit Boosted by Conformer","created":"2020-10-26","cited_by_count":132},{"id":"1909.09116","title":"Self-Training for End-to-End Speech Recognition","created":"2019-09-19","cited_by_count":129},{"id":"1911.08460","title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","created":"2019-11-19","cited_by_count":120},{"id":"2106.04732","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","created":"2021-06-08","cited_by_count":104},{"id":"1904.03416","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","created":"2019-04-06","cited_by_count":87},{"id":"2005.09267","title":"Iterative Pseudo-Labeling for Speech Recognition","created":"2020-05-19","cited_by_count":83},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77},{"id":"2010.11745","title":"Rethinking Evaluation in ASR: Are Our Models Robust Enough?","created":"2020-10-22","cited_by_count":73},{"id":"2007.15188","title":"Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability","created":"2020-07-30","cited_by_count":63},{"id":"2202.07136","title":"Debiased Self-Training for Semi-Supervised Learning","created":"2022-02-15","cited_by_count":62},{"id":"2006.04996","title":"Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation","created":"2020-06-09","cited_by_count":60},{"id":"2010.11524","title":"SlimIPL: Language-Model-Free Iterative Pseudo-Labeling","created":"2020-10-22","cited_by_count":54},{"id":"1806.02786","title":"Domain Adversarial Training for Accented Speech Recognition","created":"2018-06-07","cited_by_count":40},{"id":"2106.08922","title":"Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition","created":"2021-06-16","cited_by_count":40},{"id":"2011.13439","title":"Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training","created":"2020-11-26","cited_by_count":39},{"id":"2111.08137","title":"Joint Unsupervised and Supervised Training for Multilingual ASR","created":"2021-11-15","cited_by_count":39},{"id":"2010.11428","title":"Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition","created":"2020-10-22","cited_by_count":35},{"id":"2105.11905","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","created":"2021-05-18","cited_by_count":35},{"id":"2006.13352","title":"Rethinking Distributional Matching Based Domain Adaptation","created":"2020-06-23","cited_by_count":33},{"id":"1708.05466","title":"Large-Scale Domain Adaptation via Teacher-Student Learning","created":"2017-08-17","cited_by_count":31},{"id":"2001.09128","title":"Semi-supervised ASR by End-to-end Self-training","created":"2020-01-24","cited_by_count":29},{"id":"2104.12081","title":"How Well Does Self-Supervised Pre-Training Perform with Streaming Data?","created":"2021-04-25","cited_by_count":29},{"id":"2001.08290","title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","created":"2020-01-15","cited_by_count":28},{"id":"1707.06265","title":"Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation","created":"2017-07-19","cited_by_count":27},{"id":"2110.00165","title":"Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning","created":"2021-10-01","cited_by_count":26},{"id":"2203.12668","title":"Pseudo Label Is Better Than Human Label","created":"2022-03-22","cited_by_count":25},{"id":"2111.00161","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","created":"2021-10-30","cited_by_count":24},{"id":"2106.07759","title":"Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition","created":"2021-06-14","cited_by_count":21},{"id":"2011.00093","title":"Joint Masked CPC and CTC Training for ASR","created":"2020-10-30","cited_by_count":20},{"id":"2007.13876","title":"Semi-Supervised Learning with Data Augmentation for End-to-End ASR","created":"2020-07-27","cited_by_count":19},{"id":"2104.07474","title":"EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition","created":"2021-04-13","cited_by_count":13},{"id":"1804.00522","title":"A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation","created":"2018-03-27","cited_by_count":10},{"id":"2004.13480","title":"L-Vector: Neural Label Embedding for Domain Adaptation","created":"2020-04-25","cited_by_count":9},{"id":"2011.02774","title":"Multi-Accent Adaptation based on Gate Mechanism","created":"2020-11-05","cited_by_count":9},{"id":"2104.07491","title":"Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching","created":"2021-04-15","cited_by_count":9},{"id":"2109.05494","title":"Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages","created":"2021-09-12","cited_by_count":9},{"id":"1806.04872","title":"Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition","created":"2018-06-13","cited_by_count":7},{"id":"2110.04484","title":"Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR","created":"2021-10-09","cited_by_count":7},{"id":"2104.02558","title":"Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model","created":"2021-04-06","cited_by_count":6},{"id":"2011.02782","title":"Domain Adaptation Using Class Similarity for Robust Speech Recognition","created":"2020-11-05","cited_by_count":5}],"next_cursor":null}