{"list":"other","total":63,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"2009.00713","title":"WaveGrad: Estimating Gradients for Waveform Generation","created":"2020-09-02","cited_by_count":622},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"2003.08685","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","created":"2020-03-19","cited_by_count":504},{"id":"1902.06705","title":"On Evaluating Adversarial Robustness","created":"2019-02-18","cited_by_count":447},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"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":"1706.02633","title":"Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs","created":"2017-06-08","cited_by_count":333},{"id":"1811.00656","title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts","created":"2018-11-01","cited_by_count":319},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"id":"1907.06515","title":"Detecting and Simulating Artifacts in GAN Fake Images","created":"2019-07-15","cited_by_count":293},{"id":"2003.01826","title":"Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions","created":"2020-03-03","cited_by_count":280},{"id":"1801.01944","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","created":"2018-01-05","cited_by_count":274},{"id":"1803.01229","title":"GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification","created":"2018-03-03","cited_by_count":242},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"1812.11842","title":"Do GANs leave artificial fingerprints?","created":"2018-12-31","cited_by_count":190},{"id":"1904.05441","title":"ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection","created":"2019-04-09","cited_by_count":178},{"id":"2011.01108","title":"End-to-end anti-spoofing with RawNet2","created":"2020-11-02","cited_by_count":164},{"id":"1903.06836","title":"Detecting GAN generated Fake Images using Co-occurrence Matrices","created":"2019-03-15","cited_by_count":124},{"id":"1612.07837","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","created":"2016-12-22","cited_by_count":110},{"id":"1909.11646","title":"High Fidelity Speech Synthesis with Adversarial Networks","created":"2019-09-25","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":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"2004.10234","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","created":"2020-04-21","cited_by_count":82},{"id":"2004.00622","title":"Evading Deepfake-Image Detectors with White- and Black-Box Attacks","created":"2020-04-01","cited_by_count":80},{"id":"2006.03575","title":"End-to-End Adversarial Text-to-Speech","created":"2020-06-05","cited_by_count":77},{"id":"1812.08247","title":"Detecting GAN-generated Imagery using Color Cues","created":"2018-12-19","cited_by_count":76},{"id":"1705.08947","title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","created":"2017-05-24","cited_by_count":75},{"id":"1807.07281","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","created":"2018-07-19","cited_by_count":70},{"id":"1801.08535","title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition","created":"2018-01-24","cited_by_count":66},{"id":"2005.05106","title":"Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech","created":"2020-05-11","cited_by_count":63},{"id":"2004.03383","title":"Attribution in Scale and Space","created":"2020-04-03","cited_by_count":61},{"id":"1910.10909","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","created":"2019-10-24","cited_by_count":60},{"id":"1711.00354","title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","created":"2017-10-28","cited_by_count":58},{"id":"2102.05889","title":"ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech","created":"2021-02-11","cited_by_count":58},{"id":"1811.02155","title":"FloWaveNet : A Generative Flow for Raw Audio","created":"2018-11-06","cited_by_count":54},{"id":"1912.01219","title":"WaveFlow: A Compact Flow-based Model for Raw Audio","created":"2019-12-03","cited_by_count":51},{"id":"1801.00554","title":"Did you hear that? Adversarial Examples Against Automatic Speech Recognition","created":"2018-01-02","cited_by_count":48},{"id":"1801.01203","title":"Spectre Attacks: Exploiting Speculative Execution","created":"2018-01-03","cited_by_count":47},{"id":"1904.12088","title":"Neural source-filter waveform models for statistical parametric speech synthesis","created":"2019-04-27","cited_by_count":46},{"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":"1712.06148","title":"Generating and designing DNA with deep generative models","created":"2017-12-17","cited_by_count":30},{"id":"2011.03706","title":"ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration","created":"2020-11-07","cited_by_count":22},{"id":"1908.01551","title":"Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems","created":"2019-08-05","cited_by_count":16},{"id":"2004.00526","title":"Improved RawNet with Feature Map Scaling for Text-independent Speaker Verification using Raw Waveforms","created":"2020-04-01","cited_by_count":12},{"id":"1906.09573","title":"A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis","created":"2019-06-23","cited_by_count":10},{"id":"1810.13048","title":"Attentive Filtering Networks for Audio Replay Attack Detection","created":"2018-10-31","cited_by_count":7},{"id":"1807.04919","title":"TequilaGAN: How to easily identify GAN samples","created":"2018-07-13","cited_by_count":2}],"next_cursor":null}