{"list":"other","total":51,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2009.00713","title":"WaveGrad: Estimating Gradients for Waveform Generation","created":"2020-09-02","cited_by_count":622},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"2010.15258","title":"DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors","created":"2020-10-28","cited_by_count":241},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"2106.02808","title":"A Variational Perspective on Diffusion-Based Generative Models and Score Matching","created":"2021-06-05","cited_by_count":183},{"id":"2202.05830","title":"Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality","created":"2022-02-11","cited_by_count":182},{"id":"2110.01763","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","created":"2021-10-05","cited_by_count":172},{"id":"1710.05941","title":"Searching for Activation Functions","created":"2017-10-16","cited_by_count":169},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"2005.13981","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","created":"2020-05-16","cited_by_count":133},{"id":"1710.04196","title":"Pyroomacoustics: A Python package for audio room simulations and array processing algorithms","created":"2017-10-11","cited_by_count":132},{"id":"2008.12595","title":"Dynamical Variational Autoencoders: A Comprehensive Review","created":"2020-08-28","cited_by_count":128},{"id":"2104.03538","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","created":"2021-04-08","cited_by_count":114},{"id":"2206.03065","title":"Universal Speech Enhancement with Score-based Diffusion","created":"2022-06-07","cited_by_count":75},{"id":"1903.03107","title":"Phase-aware Speech Enhancement with Deep Complex U-Net","created":"2019-03-07","cited_by_count":73},{"id":"2203.13086","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","created":"2022-03-24","cited_by_count":49},{"id":"2203.15149","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","created":"2022-03-28","cited_by_count":45},{"id":"1710.11439","title":"Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization","created":"2017-10-31","cited_by_count":33},{"id":"1902.01605","title":"A variance modeling framework based on variational autoencoders for speech enhancement","created":"2019-02-05","cited_by_count":33},{"id":"2102.08706","title":"Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder","created":"2021-02-17","cited_by_count":28},{"id":"2106.12271","title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","created":"2021-06-23","cited_by_count":28},{"id":"2005.08138","title":"An Open source Implementation of ITU-T Recommendation P.808 with Validation","created":"2020-05-17","cited_by_count":27},{"id":"1902.06568","title":"STCN: Stochastic Temporal Convolutional Networks","created":"2019-02-18","cited_by_count":26},{"id":"2106.11789","title":"Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement","created":"2021-06-22","cited_by_count":25},{"id":"1703.02205","title":"Raw Waveform-based Speech Enhancement by Fully Convolutional Networks","created":"2017-03-07","cited_by_count":24},{"id":"1903.04567","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling","created":"2019-03-11","cited_by_count":21},{"id":"2009.12286","title":"A consolidated view of loss functions for supervised deep learning-based speech enhancement","created":"2020-09-25","cited_by_count":19},{"id":"2110.05866","title":"MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech","created":"2021-10-12","cited_by_count":18},{"id":"1704.08504","title":"Complex spectrogram enhancement by convolutional neural network with multi-metrics learning","created":"2017-04-27","cited_by_count":17},{"id":"2102.06454","title":"Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier","created":"2021-02-12","cited_by_count":12},{"id":"2105.08970","title":"Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement","created":"2021-05-19","cited_by_count":7},{"id":"2202.07931","title":"DBT-Net: Dual-branch federative magnitude and phase estimation with attention-in-attention transformer for monaural speech enhancement","created":"2022-02-16","cited_by_count":6},{"id":"2203.16222","title":"Phase-Aware Deep Speech Enhancement: It's All About The Frame Length","created":"2022-03-30","cited_by_count":5}],"next_cursor":null}