{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"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":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"2006.13979","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","created":"2020-06-24","cited_by_count":501},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"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":"1712.01769","title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":196},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"2001.09239","title":"Multi-task self-supervised learning for Robust Speech Recognition","created":"2020-01-25","cited_by_count":130},{"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":"2002.02848","title":"Unsupervised pretraining transfers well across languages","created":"2020-02-07","cited_by_count":101},{"id":"1801.00841","title":"Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer","created":"2018-01-02","cited_by_count":96},{"id":"1709.07902","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","created":"2017-09-22","cited_by_count":93},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"1901.08810","title":"Unsupervised speech representation learning using WaveNet autoencoders","created":"2019-01-25","cited_by_count":90},{"id":"1910.09799","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","created":"2019-10-22","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":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"1704.05119","title":"Exploring Sparsity in Recurrent Neural Networks","created":"2017-04-17","cited_by_count":75},{"id":"1507.08240","title":"EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding","created":"2015-07-29","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":"1712.01818","title":"Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":68},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68},{"id":"1912.01679","title":"Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition","created":"2019-12-03","cited_by_count":66},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65},{"id":"2007.00991","title":"Data Augmenting Contrastive Learning of Speech Representations in the Time Domain","created":"2020-07-02","cited_by_count":63},{"id":"2005.08575","title":"Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation","created":"2020-05-18","cited_by_count":59},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53},{"id":"1707.04879","title":"Listening while Speaking: Speech Chain by Deep Learning","created":"2017-07-16","cited_by_count":46},{"id":"1905.06791","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","created":"2019-05-13","cited_by_count":41},{"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":"2105.11905","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","created":"2021-05-18","cited_by_count":35},{"id":"1610.03022","title":"Very Deep Convolutional Networks for End-to-End Speech Recognition","created":"2016-10-10","cited_by_count":34},{"id":"1909.12408","title":"Optimizing Speech Recognition For The Edge","created":"2019-09-26","cited_by_count":32},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29},{"id":"1704.04222","title":"Learning Latent Representations for Speech Generation and Transformation","created":"2017-04-13","cited_by_count":27},{"id":"1906.10508","title":"Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations","created":"2019-06-25","cited_by_count":23},{"id":"2004.05274","title":"Improved Speech Representations with Multi-Target Autoregressive Predictive Coding","created":"2020-04-11","cited_by_count":23},{"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":"2006.02547","title":"A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning","created":"2020-06-03","cited_by_count":18},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16},{"id":"1903.12389","title":"Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet","created":"2019-03-29","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":"2203.04583","title":"Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks","created":"2022-03-09","cited_by_count":13},{"id":"1911.11935","title":"AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition","created":"2019-11-27","cited_by_count":11},{"id":"2203.16965","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","created":"2022-03-31","cited_by_count":11},{"id":"1811.08111","title":"Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision","created":"2018-11-20","cited_by_count":10},{"id":"2102.11531","title":"Memory-efficient Speech Recognition on Smart Devices","created":"2021-02-23","cited_by_count":8},{"id":"1806.06342","title":"Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin","created":"2018-06-17","cited_by_count":6},{"id":"2110.08545","title":"A Unified Speaker Adaptation Approach for ASR","created":"2021-10-16","cited_by_count":5},{"id":"2110.09930","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","created":"2021-10-18","cited_by_count":4}],"next_cursor":null}