{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"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":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"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":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"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":"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":"2003.07705","title":"Hybrid Autoregressive Transducer (hat)","created":"2020-03-12","cited_by_count":108},{"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":"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":"1905.11235","title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","created":"2019-05-27","cited_by_count":77},{"id":"2001.02674","title":"Streaming automatic speech recognition with the transformer model","created":"2020-01-08","cited_by_count":73},{"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":"1909.12415","title":"Improving RNN Transducer Modeling for End-to-End Speech Recognition","created":"2019-09-26","cited_by_count":68},{"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":"2010.14606","title":"Cascaded encoders for unifying streaming and non-streaming ASR","created":"2020-10-27","cited_by_count":53},{"id":"2005.11185","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","created":"2020-05-22","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":"1707.07413","title":"Exploring Neural Transducers for End-to-End Speech Recognition","created":"2017-07-24","cited_by_count":44},{"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":"2011.03072","title":"Alignment Restricted Streaming Recurrent Neural Network Transducer","created":"2020-11-05","cited_by_count":42},{"id":"2011.06110","title":"Efficient Knowledge Distillation for RNN-Transducer Models","created":"2020-11-11","cited_by_count":38},{"id":"1906.00672","title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","created":"2019-06-03","cited_by_count":33},{"id":"1507.06947","title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","created":"2015-07-24","cited_by_count":26},{"id":"2003.10369","title":"Low Latency End-to-End Streaming Speech Recognition with a Scout Network","created":"2020-03-23","cited_by_count":20},{"id":"2010.03449","title":"Super-Human Performance in Online Low-latency Recognition of Conversational Speech","created":"2020-10-07","cited_by_count":20},{"id":"2004.05009","title":"Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR","created":"2020-04-10","cited_by_count":19},{"id":"1904.08311","title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","created":"2019-04-17","cited_by_count":18},{"id":"1912.03010","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","created":"2019-12-06","cited_by_count":18},{"id":"2001.00577","title":"Attention based on-device streaming speech recognition with large speech corpus","created":"2020-01-02","cited_by_count":18},{"id":"1510.08983","title":"Highway Long Short-Term Memory RNNs for Distant Speech Recognition","created":"2015-10-30","cited_by_count":17},{"id":"2005.09394","title":"Enhancing Monotonic Multihead Attention for Streaming ASR","created":"2020-05-19","cited_by_count":16},{"id":"1711.02212","title":"Improved training for online end-to-end speech recognition systems","created":"2017-11-06","cited_by_count":13},{"id":"1811.05247","title":"An Online Attention-based Model for Speech Recognition","created":"2018-11-13","cited_by_count":13},{"id":"2006.01712","title":"Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition","created":"2020-05-21","cited_by_count":12},{"id":"2008.05514","title":"Online Automatic Speech Recognition with Listen, Attend and Spell Model","created":"2020-08-12","cited_by_count":10},{"id":"1811.04531","title":"Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition","created":"2018-11-12","cited_by_count":9},{"id":"2005.00572","title":"Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition","created":"2020-05-01","cited_by_count":9},{"id":"1712.01807","title":"Improving the Performance of Online Neural Transducer Models","created":"2017-12-05","cited_by_count":7},{"id":"1902.01955","title":"On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition","created":"2019-02-05","cited_by_count":7},{"id":"2006.01416","title":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer","created":"2020-06-02","cited_by_count":7},{"id":"1511.04868","title":"A Neural Transducer","created":"2015-11-16","cited_by_count":6},{"id":"1608.01281","title":"Learning Online Alignments with Continuous Rewards Policy Gradient","created":"2016-08-03","cited_by_count":6},{"id":"1808.10088","title":"End-to-end Speech Recognition with Adaptive Computation Steps","created":"2018-08-30","cited_by_count":5},{"id":"1912.12384","title":"Improved Multi-Stage Training of Online Attention-based Encoder-Decoder Models","created":"2019-12-28","cited_by_count":5},{"id":"2011.13834","title":"Transformer-based Online Speech Recognition with Decoder-end Adaptive Computation Steps","created":"2020-11-27","cited_by_count":5},{"id":"1910.11871","title":"Towards Online End-to-end Transformer Automatic Speech Recognition","created":"2019-10-25","cited_by_count":3},{"id":"2005.04712","title":"CTC-synchronous Training for Monotonic Attention Model","created":"2020-05-10","cited_by_count":3},{"id":"2003.09891","title":"Low Latency ASR for Simultaneous Speech Translation","created":"2020-03-22","cited_by_count":2},{"id":"2006.04928","title":"Learning to Count Words in Fluent Speech enables Online Speech Recognition","created":"2020-06-08","cited_by_count":2},{"id":"1706.06428","title":"An online sequence-to-sequence model for noisy speech recognition","created":"2017-06-16","cited_by_count":1},{"id":"2011.02127","title":"Sequence-to-Sequence Learning via Attention Transfer for Incremental Speech Recognition","created":"2020-11-04","cited_by_count":1}],"next_cursor":null}