{"list":"other","total":195,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"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":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"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":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1706.03872","title":"Six Challenges for Neural Machine Translation","created":"2017-06-12","cited_by_count":335},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"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":"2002.02562","title":"Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss","created":"2020-02-07","cited_by_count":235},{"id":"1811.06621","title":"Streaming End-to-end Speech Recognition For Mobile Devices","created":"2018-11-15","cited_by_count":234},{"id":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"id":"1712.01769","title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","created":"2017-12-05","cited_by_count":196},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"1503.03535","title":"On Using Monolingual Corpora in Neural Machine Translation","created":"2015-03-11","cited_by_count":150},{"id":"1511.06807","title":"Adding Gradient Noise Improves Learning for Very Deep Networks","created":"2015-11-21","cited_by_count":145},{"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":"1808.04444","title":"Character-Level Language Modeling with Deeper Self-Attention","created":"2018-08-09","cited_by_count":138},{"id":"1808.02480","title":"Deep context: end-to-end contextual speech recognition","created":"2018-08-07","cited_by_count":137},{"id":"2010.13956","title":"Recent Developments on ESPnet Toolkit Boosted by Conformer","created":"2020-10-26","cited_by_count":132},{"id":"2102.01547","title":"WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit","created":"2021-02-02","cited_by_count":125},{"id":"1808.10006","title":"Correcting Length Bias in Neural Machine Translation","created":"2018-08-29","cited_by_count":120},{"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":"1908.10090","title":"On NMT Search Errors and Model Errors: Cat Got Your Tongue?","created":"2019-08-27","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":"1712.01996","title":"An analysis of incorporating an external language model into a sequence-to-sequence model","created":"2017-12-06","cited_by_count":111},{"id":"1601.04811","title":"Modeling Coverage for Neural Machine Translation","created":"2016-01-19","cited_by_count":110},{"id":"2007.03001","title":"Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters","created":"2020-07-06","cited_by_count":110},{"id":"2003.07705","title":"Hybrid Autoregressive Transducer (hat)","created":"2020-03-12","cited_by_count":108},{"id":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108},{"id":"1906.05218","title":"Monotonic Infinite Lookback Attention for Simultaneous Machine Translation","created":"2019-06-12","cited_by_count":104},{"id":"1612.02695","title":"Towards better decoding and language model integration in sequence to sequence models","created":"2016-12-08","cited_by_count":100},{"id":"2003.12710","title":"A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency","created":"2020-03-28","cited_by_count":100},{"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":"2010.11395","title":"Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset","created":"2020-10-22","cited_by_count":97},{"id":"1905.04226","title":"Language Modeling with Deep Transformers","created":"2019-05-10","cited_by_count":96},{"id":"2102.03216","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","created":"2021-02-05","cited_by_count":96},{"id":"1909.05330","title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","created":"2019-09-11","cited_by_count":93},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91},{"id":"1708.06426","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","created":"2017-08-21","cited_by_count":88},{"id":"1910.09799","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","created":"2019-10-22","cited_by_count":88},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88},{"id":"1902.08295","title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","created":"2019-02-21","cited_by_count":86},{"id":"1704.00784","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","created":"2017-04-03","cited_by_count":85},{"id":"1712.05382","title":"Monotonic Chunkwise Attention","created":"2017-12-14","cited_by_count":83},{"id":"2011.01991","title":"Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition","created":"2020-11-03","cited_by_count":80},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79},{"id":"1905.11235","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","created":"2019-05-27","cited_by_count":77},{"id":"2005.08700","title":"Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict","created":"2020-05-18","cited_by_count":76},{"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":"2001.02674","title":"Streaming automatic speech recognition with the transformer model","created":"2020-01-08","cited_by_count":73},{"id":"2002.11268","title":"A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition","created":"2020-02-26","cited_by_count":73},{"id":"1910.12977","title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","created":"2019-10-28","cited_by_count":69},{"id":"2011.10798","title":"A Better and Faster End-to-End Model for Streaming ASR","created":"2020-11-21","cited_by_count":69},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"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":"2002.08926","title":"Imputer: Sequence Modelling via Imputation and Dynamic Programming","created":"2020-02-20","cited_by_count":66},{"id":"1908.10992","title":"Two-Pass End-to-End Speech Recognition","created":"2019-08-29","cited_by_count":64},{"id":"2204.05409","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","created":"2022-04-11","cited_by_count":64},{"id":"1905.03072","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","created":"2019-05-08","cited_by_count":63},{"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":"2104.02724","title":"Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions","created":"2021-04-06","cited_by_count":61},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61},{"id":"1912.05533","title":"SpecAugment on Large Scale Datasets","created":"2019-12-11","cited_by_count":60},{"id":"1803.00144","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","created":"2018-03-01","cited_by_count":58},{"id":"2003.07962","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","created":"2020-03-17","cited_by_count":57},{"id":"1606.01305","title":"Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations","created":"2016-06-03","cited_by_count":54},{"id":"2010.14606","title":"Cascaded encoders for unifying streaming and non-streaming ASR","created":"2020-10-27","cited_by_count":53},{"id":"2004.11544","title":"Towards Fast and Accurate Streaming End-to-End ASR","created":"2020-04-24","cited_by_count":47},{"id":"1707.04879","title":"Listening while Speaking: Speech Chain by Deep Learning","created":"2017-07-16","cited_by_count":46},{"id":"1904.13377","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","created":"2019-04-30","cited_by_count":46}],"next_cursor":"100"}