{"list":"other","total":247,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","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":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"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":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"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":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"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":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"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":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"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":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","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":"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":"1703.08581","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","created":"2017-03-24","cited_by_count":121},{"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":"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":"1906.05218","title":"Monotonic Infinite Lookback Attention for Simultaneous Machine Translation","created":"2019-06-12","cited_by_count":104},{"id":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101},{"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":"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":"1909.05330","title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","created":"2019-09-11","cited_by_count":93},{"id":"1708.06426","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","created":"2017-08-21","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":"1711.01694","title":"Multilingual Speech Recognition With A Single End-To-End Model","created":"2017-11-06","cited_by_count":87},{"id":"2003.12687","title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","created":"2020-03-28","cited_by_count":87},{"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":"2006.03411","title":"Contextual RNN-T For Open Domain ASR","created":"2020-06-04","cited_by_count":85},{"id":"1712.05382","title":"Monotonic Chunkwise Attention","created":"2017-12-14","cited_by_count":83},{"id":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"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":"1905.11235","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","created":"2019-05-27","cited_by_count":77},{"id":"1910.11455","title":"Recognizing long-form speech using streaming end-to-end models","created":"2019-10-24","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":"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":"1802.06424","title":"End-to-end Audiovisual Speech Recognition","created":"2018-02-18","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":"2010.11148","title":"FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization","created":"2020-10-21","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":"1412.1602","title":"End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results","created":"2014-12-04","cited_by_count":68},{"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":"1909.12415","title":"Improving RNN Transducer Modeling for End-to-End Speech Recognition","created":"2019-09-26","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":"1807.10857","title":"A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition","created":"2018-07-27","cited_by_count":66},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"1908.10992","title":"Two-Pass End-to-End Speech Recognition","created":"2019-08-29","cited_by_count":64},{"id":"2011.07754","title":"Deep Shallow Fusion for RNN-T Personalization","created":"2020-11-16","cited_by_count":64},{"id":"1902.07178","title":"A spelling correction model for end-to-end speech recognition","created":"2019-02-19","cited_by_count":63},{"id":"2005.14327","title":"On the Comparison of Popular End-to-End Models for Large Scale Speech Recognition","created":"2020-05-28","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":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61},{"id":"2003.07962","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","created":"2020-03-17","cited_by_count":57},{"id":"1811.09021","title":"Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes","created":"2018-11-22","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":"2104.00235","title":"Multilingual and code-switching ASR challenges for low resource Indian languages","created":"2021-04-01","cited_by_count":53},{"id":"1907.05337","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","created":"2019-07-09","cited_by_count":49},{"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":"1707.07413","title":"Exploring Neural Transducers for End-to-End Speech Recognition","created":"2017-07-24","cited_by_count":44},{"id":"1910.06522","title":"MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition","created":"2019-10-15","cited_by_count":44},{"id":"2103.09935","title":"Advancing RNN Transducer Technology for Speech Recognition","created":"2021-03-17","cited_by_count":44},{"id":"1609.03193","title":"Wav2Letter: an End-to-End ConvNet-based Speech Recognition System","created":"2016-09-11","cited_by_count":43},{"id":"1706.02737","title":"Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM","created":"2017-06-08","cited_by_count":43},{"id":"1911.02242","title":"A comparison of end-to-end models for long-form speech recognition","created":"2019-11-06","cited_by_count":42},{"id":"2002.03921","title":"End-to-End Multi-speaker Speech Recognition with Transformer","created":"2020-02-10","cited_by_count":42},{"id":"2007.05609","title":"Class LM and word mapping for contextual biasing in End-to-End ASR","created":"2020-07-10","cited_by_count":42},{"id":"2011.03072","title":"Alignment Restricted Streaming Recurrent Neural Network Transducer","created":"2020-11-05","cited_by_count":42},{"id":"1912.09251","title":"Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities","created":"2019-12-14","cited_by_count":41},{"id":"2006.10930","title":"Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers","created":"2020-06-19","cited_by_count":41},{"id":"2008.03822","title":"Distilling the Knowledge of BERT for Sequence-to-Sequence ASR","created":"2020-08-09","cited_by_count":41},{"id":"2011.11564","title":"Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems","created":"2020-11-23","cited_by_count":41},{"id":"2011.06110","title":"Efficient Knowledge Distillation for RNN-Transducer Models","created":"2020-11-11","cited_by_count":38},{"id":"1712.01541","title":"Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model","created":"2017-12-05","cited_by_count":37},{"id":"1910.00254","title":"Multilingual End-to-End Speech Translation","created":"2019-10-01","cited_by_count":37},{"id":"2102.01380","title":"Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition","created":"2021-02-02","cited_by_count":37},{"id":"1805.03294","title":"Improved training of end-to-end attention models for speech recognition","created":"2018-05-08","cited_by_count":36}],"next_cursor":"100"}