{"list":"other","total":86,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1808.00158","title":"Speaker Recognition from Raw Waveform with SincNet","created":"2018-07-29","cited_by_count":166},{"id":"1808.10583","title":"AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale","created":"2018-08-31","cited_by_count":128},{"id":"2006.05278","title":"An Overview of Deep Semi-Supervised Learning","created":"2020-06-09","cited_by_count":121},{"id":"1711.07128","title":"Hello Edge: Keyword Spotting on Microcontrollers","created":"2017-11-20","cited_by_count":110},{"id":"1810.05512","title":"Federated Learning for Keyword Spotting","created":"2018-10-09","cited_by_count":95},{"id":"1912.13200","title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","created":"2019-12-31","cited_by_count":82},{"id":"1606.08165","title":"Supervised learning based on temporal coding in spiking neural networks","created":"2016-06-27","cited_by_count":76},{"id":"1911.04890","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","created":"2019-11-08","cited_by_count":74},{"id":"1710.10361","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","created":"2017-10-28","cited_by_count":68},{"id":"2104.00769","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","created":"2021-04-01","cited_by_count":60},{"id":"2012.00931","title":"Speaker Recognition Based on Deep Learning: An Overview","created":"2020-12-02","cited_by_count":59},{"id":"1904.03814","title":"Temporal Convolution for Real-time Keyword Spotting on Mobile Devices","created":"2019-04-08","cited_by_count":49},{"id":"2106.04140","title":"Broadcasted Residual Learning for Efficient Keyword Spotting","created":"2021-06-08","cited_by_count":48},{"id":"2005.06720","title":"Streaming keyword spotting on mobile devices","created":"2020-05-14","cited_by_count":47},{"id":"1808.08929","title":"A neural attention model for speech command recognition","created":"2018-08-27","cited_by_count":45},{"id":"2001.01656","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","created":"2020-01-06","cited_by_count":38},{"id":"2103.09963","title":"TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain","created":"2021-03-18","cited_by_count":36},{"id":"1603.00982","title":"Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder","created":"2016-03-03","cited_by_count":34},{"id":"1906.03588","title":"rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method","created":"2019-06-09","cited_by_count":34},{"id":"1607.05666","title":"Trainable Frontend For Robust and Far-Field Keyword Spotting","created":"2016-07-19","cited_by_count":33},{"id":"1703.05390","title":"Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting","created":"2017-03-15","cited_by_count":32},{"id":"1705.10874","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","created":"2017-05-30","cited_by_count":30},{"id":"1812.02802","title":"End-to-End Streaming Keyword Spotting","created":"2018-12-06","cited_by_count":25},{"id":"2102.07061","title":"Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss","created":"2021-02-14","cited_by_count":25},{"id":"2009.01225","title":"Seeing wake words: Audio-visual Keyword Spotting","created":"2020-09-02","cited_by_count":22},{"id":"1811.07684","title":"Efficient keyword spotting using dilated convolutions and gating","created":"2018-11-19","cited_by_count":21},{"id":"1911.02086","title":"Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions","created":"2019-11-05","cited_by_count":20},{"id":"2002.01322","title":"Training Keyword Spotters with Limited and Synthesized Speech Data","created":"2020-01-31","cited_by_count":20},{"id":"1710.09617","title":"Streaming Small-Footprint Keyword Spotting using Sequence-to-Sequence Models","created":"2017-10-26","cited_by_count":19},{"id":"1910.05171","title":"Query-by-example on-device keyword spotting","created":"2019-10-11","cited_by_count":19},{"id":"1803.10916","title":"Attention-based End-to-End Models for Small-Footprint Keyword Spotting","created":"2018-03-29","cited_by_count":18},{"id":"1803.10109","title":"Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline","created":"2018-03-27","cited_by_count":17},{"id":"1705.02411","title":"Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting","created":"2017-05-05","cited_by_count":15},{"id":"1811.10736","title":"DONUT: CTC-based Query-by-Example Keyword Spotting","created":"2018-11-26","cited_by_count":15},{"id":"2004.12200","title":"Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-footprint Keyword Spotting","created":"2020-04-25","cited_by_count":15},{"id":"2010.09960","title":"Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution","created":"2020-10-20","cited_by_count":15},{"id":"1811.05250","title":"Modality Attention for End-to-End Audio-visual Speech Recognition","created":"2018-11-13","cited_by_count":13},{"id":"2010.06659","title":"Towards Data-efficient Modeling for Wake Word Spotting","created":"2020-10-13","cited_by_count":13},{"id":"2009.00165","title":"Neural Architecture Search For Keyword Spotting","created":"2020-09-01","cited_by_count":11},{"id":"1806.07098","title":"End-to-End Speech Recognition From the Raw Waveform","created":"2018-06-19","cited_by_count":10},{"id":"1912.07575","title":"Predicting detection filters for small footprint open-vocabulary keyword spotting","created":"2019-12-16","cited_by_count":10},{"id":"2001.09246","title":"Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling","created":"2020-01-25","cited_by_count":10},{"id":"2009.03658","title":"AutoKWS: Keyword Spotting with Differentiable Architecture Search","created":"2020-09-08","cited_by_count":10},{"id":"2106.01604","title":"Noisy student-teacher training for robust keyword spotting","created":"2021-06-03","cited_by_count":10},{"id":"2001.10816","title":"Multi-task Learning for Speaker Verification and Voice Trigger Detection","created":"2020-01-26","cited_by_count":9},{"id":"2005.03867","title":"Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention","created":"2020-05-08","cited_by_count":9},{"id":"2005.08776","title":"Metric Learning for Keyword Spotting","created":"2020-05-18","cited_by_count":9},{"id":"1804.09298","title":"Recent Progresses in Deep Learning based Acoustic Models (Updated)","created":"2018-04-25","cited_by_count":8},{"id":"2008.03405","title":"Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection","created":"2020-08-08","cited_by_count":8},{"id":"2104.13970","title":"Personalized Keyphrase Detection using Speaker and Environment Information","created":"2021-04-28","cited_by_count":8},{"id":"2105.06598","title":"Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation","created":"2021-05-14","cited_by_count":8},{"id":"1806.09374","title":"Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring","created":"2018-06-25","cited_by_count":7},{"id":"1912.05124","title":"Small-footprint Keyword Spotting with Graph Convolutional Network","created":"2019-12-11","cited_by_count":7},{"id":"1905.04554","title":"Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification","created":"2019-05-11","cited_by_count":6},{"id":"1910.04500","title":"Orthogonality Constrained Multi-Head Attention For Keyword Spotting","created":"2019-10-10","cited_by_count":6},{"id":"2008.09606","title":"Howl: A Deployed, Open-Source Wake Word Detection System","created":"2020-08-21","cited_by_count":6},{"id":"1807.04353","title":"Efficient keyword spotting using time delay neural networks","created":"2018-07-11","cited_by_count":5},{"id":"2010.06676","title":"On Front-end Gain Invariant Modeling for Wake Word Spotting","created":"2020-10-13","cited_by_count":5},{"id":"2006.00217","title":"Exploring Filterbank Learning for Keyword Spotting","created":"2020-05-30","cited_by_count":4},{"id":"1906.09417","title":"Keyword Spotting for Hearing Assistive Devices Robust to External Speakers","created":"2019-06-22","cited_by_count":3},{"id":"2108.05516","title":"Text Anchor Based Metric Learning for Small-footprint Keyword Spotting","created":"2021-08-12","cited_by_count":3},{"id":"1906.08415","title":"A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting","created":"2019-06-20","cited_by_count":2},{"id":"2005.03633","title":"Domain Aware Training for Far-field Small-footprint Keyword Spotting","created":"2020-05-07","cited_by_count":2},{"id":"2104.00513","title":"Auto-KWS 2021 Challenge: Task, Datasets, and Baselines","created":"2021-03-31","cited_by_count":2},{"id":"2005.10386","title":"End-to-End Multi-Look Keyword Spotting","created":"2020-05-20","cited_by_count":1}],"next_cursor":null}