{"list":"other","total":55,"rows":[{"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":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"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":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"1611.02770","title":"Delving into Transferable Adversarial Examples and Black-box Attacks","created":"2016-11-08","cited_by_count":536},{"id":"1902.06705","title":"On Evaluating Adversarial Robustness","created":"2019-02-18","cited_by_count":447},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"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":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205},{"id":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193},{"id":"2302.04578","title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","created":"2023-02-09","cited_by_count":167},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"1903.10346","title":"Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition","created":"2019-03-22","cited_by_count":124},{"id":"1802.06182","title":"CREPE: A Convolutional Representation for Pitch Estimation","created":"2018-02-17","cited_by_count":110},{"id":"1808.05665","title":"Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding","created":"2018-08-16","cited_by_count":85},{"id":"2012.06659","title":"DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization","created":"2020-12-11","cited_by_count":77},{"id":"2010.04055","title":"A Unified Approach to Interpreting and Boosting Adversarial Transferability","created":"2020-10-08","cited_by_count":71},{"id":"2106.09898","title":"Bad Characters: Imperceptible NLP Attacks","created":"2021-06-18","cited_by_count":71},{"id":"1911.01840","title":"Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems","created":"2019-11-03","cited_by_count":67},{"id":"1801.08535","title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition","created":"2018-01-24","cited_by_count":66},{"id":"2112.10358","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","created":"2021-12-20","cited_by_count":60},{"id":"2107.10394","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","created":"2021-07-21","cited_by_count":58},{"id":"2007.06622","title":"SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems","created":"2020-07-13","cited_by_count":46},{"id":"1901.07846","title":"SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems","created":"2019-01-23","cited_by_count":34},{"id":"2306.14422","title":"The Singing Voice Conversion Challenge 2023","created":"2023-06-26","cited_by_count":25},{"id":"2005.08781","title":"Defending Your Voice: Adversarial Attack on Voice Conversion","created":"2020-05-18","cited_by_count":23},{"id":"2206.03393","title":"Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition","created":"2022-06-07","cited_by_count":23},{"id":"2303.01507","title":"Defending against Adversarial Audio via Diffusion Model","created":"2023-03-02","cited_by_count":23},{"id":"2005.03215","title":"AutoSpeech: Neural Architecture Search for Speaker Recognition","created":"2020-05-07","cited_by_count":17},{"id":"2210.00957","title":"UnGANable: Defending Against GAN-based Face Manipulation","created":"2022-10-03","cited_by_count":15},{"id":"2001.07044","title":"JVS-MuSiC: Japanese multispeaker singing-voice corpus","created":"2020-01-20","cited_by_count":14},{"id":"2305.05736","title":"VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation","created":"2023-05-09","cited_by_count":14},{"id":"2206.13991","title":"Increasing Confidence in Adversarial Robustness Evaluations","created":"2022-06-28","cited_by_count":12},{"id":"2206.03351","title":"AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems","created":"2022-06-07","cited_by_count":10},{"id":"2305.14097","title":"QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems","created":"2023-05-23","cited_by_count":9},{"id":"2308.01040","title":"Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time","created":"2023-08-02","cited_by_count":8},{"id":"2312.04919","title":"Neural Concatenative Singing Voice Conversion: Rethinking Concatenation-Based Approach for One-Shot Singing Voice Conversion","created":"2023-12-08","cited_by_count":7},{"id":"2206.13762","title":"A Hierarchical Speaker Representation Framework for One-shot Singing Voice Conversion","created":"2022-06-28","cited_by_count":6}],"next_cursor":null}