{"list":"other","total":127,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"1804.00792","title":"Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks","created":"2018-04-03","cited_by_count":519},{"id":"1811.00636","title":"Spectral Signatures in Backdoor Attacks","created":"2018-11-01","cited_by_count":484},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"1811.03728","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","created":"2018-11-09","cited_by_count":456},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1712.02976","title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser","created":"2017-12-08","cited_by_count":329},{"id":"1703.09207","title":"Fairness in Criminal Justice Risk Assessments: The State of the Art","created":"2017-03-27","cited_by_count":315},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1801.01944","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","created":"2018-01-05","cited_by_count":274},{"id":"1807.11714","title":"Gender Bias in Neural Natural Language Processing","created":"2018-07-31","cited_by_count":211},{"id":"1708.08689","title":"Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization","created":"2017-08-29","cited_by_count":197},{"id":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"2009.02276","title":"Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching","created":"2020-09-04","cited_by_count":163},{"id":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157},{"id":"2010.06121","title":"To be Robust or to be Fair: Towards Fairness in Adversarial Training","created":"2020-10-13","cited_by_count":137},{"id":"1903.10346","title":"Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition","created":"2019-03-22","cited_by_count":124},{"id":"2010.14794","title":"Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset","created":"2020-10-28","cited_by_count":121},{"id":"1810.05512","title":"Federated Learning for Keyword Spotting","created":"2018-10-09","cited_by_count":95},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93},{"id":"1803.10609","title":"The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines","created":"2018-03-28","cited_by_count":92},{"id":"1808.05665","title":"Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding","created":"2018-08-16","cited_by_count":85},{"id":"1812.04218","title":"Learning Controllable Fair Representations","created":"2018-12-11","cited_by_count":83},{"id":"2002.06483","title":"Face Recognition: Too Bias, or Not Too Bias?","created":"2020-02-16","cited_by_count":82},{"id":"2011.03731","title":"On the Privacy Risks of Algorithmic Fairness","created":"2020-11-07","cited_by_count":82},{"id":"2004.12254","title":"Privacy in Deep Learning: A Survey","created":"2020-04-25","cited_by_count":71},{"id":"2011.11819","title":"When Machine Learning Meets Privacy: A Survey and Outlook","created":"2020-11-24","cited_by_count":68},{"id":"1911.01840","title":"Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems","created":"2019-11-03","cited_by_count":67},{"id":"1707.06728","title":"Efficient Defenses Against Adversarial Attacks","created":"2017-07-21","cited_by_count":53},{"id":"1703.01340","title":"Generative Poisoning Attack Method Against Neural Networks","created":"2017-03-03","cited_by_count":52},{"id":"2110.06309","title":"Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition","created":"2021-10-12","cited_by_count":49},{"id":"1801.00554","title":"Did you hear that? Adversarial Examples Against Automatic Speech Recognition","created":"2018-01-02","cited_by_count":48},{"id":"2010.15965","title":"Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework","created":"2020-10-29","cited_by_count":46},{"id":"2109.00648","title":"The VoicePrivacy 2020 Challenge: Results and findings","created":"2021-09-01","cited_by_count":46},{"id":"1810.11793","title":"Robust Audio Adversarial Example for a Physical Attack","created":"2018-10-28","cited_by_count":44},{"id":"1806.02786","title":"Domain Adversarial Training for Accented Speech Recognition","created":"2018-06-07","cited_by_count":40},{"id":"2103.03344","title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","created":"2021-03-04","cited_by_count":40},{"id":"1910.05262","title":"Hear \"No Evil\", See \"Kenansville\": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems","created":"2019-10-11","cited_by_count":38},{"id":"1809.10875","title":"Characterizing Audio Adversarial Examples Using Temporal Dependency","created":"2018-09-28","cited_by_count":36},{"id":"2005.10406","title":"Training Keyword Spotting Models on Non-IID Data with Federated Learning","created":"2020-05-21","cited_by_count":36},{"id":"2104.00682","title":"Multiview Pseudo-Labeling for Semi-supervised Learning from Video","created":"2021-04-01","cited_by_count":32},{"id":"1711.03280","title":"Crafting Adversarial Examples For Speech Paralinguistics Applications","created":"2017-11-09","cited_by_count":30},{"id":"2008.02651","title":"Improving on-device speaker verification using federated learning with privacy","created":"2020-08-06","cited_by_count":30},{"id":"2207.11345","title":"Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities","created":"2022-07-22","cited_by_count":28},{"id":"2005.08601","title":"Design Choices for X-vector Based Speaker Anonymization","created":"2020-05-18","cited_by_count":27},{"id":"2111.09983","title":"Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions","created":"2021-11-18","cited_by_count":26},{"id":"1905.07082","title":"The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services","created":"2019-05-17","cited_by_count":25},{"id":"2007.15064","title":"Privacy-preserving Voice Analysis via Disentangled Representations","created":"2020-07-29","cited_by_count":24},{"id":"1910.13212","title":"Privacy Enhanced Multimodal Neural Representations for Emotion Recognition","created":"2019-10-29","cited_by_count":22},{"id":"1911.04913","title":"Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?","created":"2019-11-12","cited_by_count":22},{"id":"1810.06828","title":"The State of Speech in HCI: Trends, Themes and Challenges","created":"2018-10-16","cited_by_count":21},{"id":"2102.04429","title":"Federated Acoustic Modeling For Automatic Speech Recognition","created":"2021-02-08","cited_by_count":20},{"id":"2111.05113","title":"Membership Inference Attacks Against Self-supervised Speech Models","created":"2021-11-09","cited_by_count":16},{"id":"2210.15707","title":"FedAudio: A Federated Learning Benchmark for Audio Tasks","created":"2022-10-27","cited_by_count":16},{"id":"2106.03785","title":"Generative Adversarial Networks: A Survey Towards Private and Secure Applications","created":"2021-06-07","cited_by_count":15},{"id":"2204.01397","title":"A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems","created":"2022-04-04","cited_by_count":15},{"id":"1909.04198","title":"Preech: A System for Privacy-Preserving Speech Transcription","created":"2019-09-09","cited_by_count":14},{"id":"2109.15108","title":"Federated Learning in ASR: Not as Easy as You Think","created":"2021-09-30","cited_by_count":14},{"id":"2110.05607","title":"Partial Variable Training for Efficient On-Device Federated Learning","created":"2021-10-11","cited_by_count":14},{"id":"2003.08474","title":"TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers","created":"2020-03-18","cited_by_count":13},{"id":"2012.04454","title":"Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation","created":"2020-12-08","cited_by_count":13},{"id":"2109.09061","title":"Model-Based Approach for Measuring the Fairness in ASR","created":"2021-09-19","cited_by_count":13},{"id":"2004.07442","title":"Voice-Indistinguishability: Protecting Voiceprint in Privacy-Preserving Speech Data Release","created":"2020-04-16","cited_by_count":12},{"id":"2110.03634","title":"Enabling On-Device Training of Speech Recognition Models with Federated Dropout","created":"2021-10-07","cited_by_count":12},{"id":"2112.13416","title":"Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings","created":"2021-12-26","cited_by_count":12},{"id":"2203.08810","title":"Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling","created":"2022-03-15","cited_by_count":12},{"id":"2010.15716","title":"Playing a Part: Speaker Verification at the Movies","created":"2020-10-29","cited_by_count":11},{"id":"2111.03777","title":"Privacy attacks for automatic speech recognition acoustic models in a federated learning framework","created":"2021-11-06","cited_by_count":10},{"id":"2201.04583","title":"VoxSRC 2021: The Third VoxCeleb Speaker Recognition Challenge","created":"2022-01-12","cited_by_count":10},{"id":"2204.09606","title":"Detecting Unintended Memorization in Language-Model-Fused ASR","created":"2022-04-20","cited_by_count":10},{"id":"2204.10242","title":"The 2021 NIST Speaker Recognition Evaluation","created":"2022-04-21","cited_by_count":10},{"id":"2208.10497","title":"Are disentangled representations all you need to build speaker anonymization systems?","created":"2022-08-22","cited_by_count":10}],"next_cursor":"100"}