{"list":"other","total":83,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"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":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"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":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"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":"2005.00561","title":"When BERT Plays the Lottery, All Tickets Are Winning","created":"2020-05-01","cited_by_count":114},{"id":"2010.10759","title":"Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition","created":"2020-10-21","cited_by_count":113},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"2007.03001","title":"Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters","created":"2020-07-06","cited_by_count":110},{"id":"2002.02848","title":"Unsupervised pretraining transfers well across languages","created":"2020-02-07","cited_by_count":101},{"id":"2010.11430","title":"Self-training and Pre-training are Complementary for Speech Recognition","created":"2020-10-22","cited_by_count":99},{"id":"2005.03191","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","created":"2020-05-07","cited_by_count":97},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"2012.06908","title":"The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models","created":"2020-12-12","cited_by_count":91},{"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":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","cited_by_count":73},{"id":"1911.03912","title":"Effectiveness of self-supervised pre-training for speech recognition","created":"2019-11-10","cited_by_count":72},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61},{"id":"2005.01172","title":"Similarity Analysis of Contextual Word Representation Models","created":"2020-05-03","cited_by_count":54},{"id":"2105.03036","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","created":"2021-05-07","cited_by_count":48},{"id":"2011.00406","title":"Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies","created":"2020-11-01","cited_by_count":47},{"id":"2001.10603","title":"Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction","created":"2020-01-28","cited_by_count":38},{"id":"2011.06110","title":"Efficient Knowledge Distillation for RNN-Transducer Models","created":"2020-11-11","cited_by_count":38},{"id":"2008.05773","title":"Continuous Speech Separation with Conformer","created":"2020-08-13","cited_by_count":36},{"id":"2010.13826","title":"Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining","created":"2020-10-26","cited_by_count":35},{"id":"1805.07467","title":"Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces","created":"2018-05-18","cited_by_count":34},{"id":"1810.03459","title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","created":"2018-10-04","cited_by_count":34},{"id":"2010.13991","title":"Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning","created":"2020-10-27","cited_by_count":34},{"id":"2103.16776","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","created":"2021-03-31","cited_by_count":33},{"id":"1709.04482","title":"Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems","created":"2017-09-13","cited_by_count":32},{"id":"1909.12408","title":"Optimizing Speech Recognition For The Edge","created":"2019-09-26","cited_by_count":32},{"id":"2010.11481","title":"Similarity Analysis of Self-Supervised Speech Representations","created":"2020-10-22","cited_by_count":26},{"id":"2005.10627","title":"Dynamic Sparsity Neural Networks for Automatic Speech Recognition","created":"2020-05-16","cited_by_count":23},{"id":"2101.06856","title":"Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devices","created":"2021-01-18","cited_by_count":19},{"id":"2104.01894","title":"Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval","created":"2021-04-05","cited_by_count":19},{"id":"2104.03416","title":"Pushing the Limits of Non-Autoregressive Speech Recognition","created":"2021-04-07","cited_by_count":18},{"id":"1907.04224","title":"Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition","created":"2019-07-09","cited_by_count":16},{"id":"2001.09727","title":"Scaling Up Online Speech Recognition Using ConvNets","created":"2020-01-27","cited_by_count":16},{"id":"1904.01575","title":"Contrastive Predictive Coding Based Feature for Automatic Speaker Verification","created":"2019-04-01","cited_by_count":15},{"id":"2104.11946","title":"Aligned Contrastive Predictive Coding","created":"2021-04-24","cited_by_count":15},{"id":"2104.06865","title":"Efficient conformer-based speech recognition with linear attention","created":"2021-04-14","cited_by_count":13},{"id":"2010.06030","title":"Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling","created":"2020-10-12","cited_by_count":9},{"id":"2009.13270","title":"Dissecting Lottery Ticket Transformers: Structural and Behavioral Study of Sparse Neural Machine Translation","created":"2020-09-17","cited_by_count":8},{"id":"2102.11531","title":"Memory-efficient Speech Recognition on Smart Devices","created":"2021-02-23","cited_by_count":8},{"id":"2103.00816","title":"Contrastive Separative Coding for Self-supervised Representation Learning","created":"2021-03-01","cited_by_count":3}],"next_cursor":null}