{"list":"other","total":132,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"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":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1803.04189","title":"Noise2Noise: Learning Image Restoration without Clean Data","created":"2018-03-12","cited_by_count":533},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"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":"2208.11970","title":"Understanding Diffusion Models: A Unified Perspective","created":"2022-08-25","cited_by_count":340},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"1701.00160","title":"NIPS 2016 Tutorial: Generative Adversarial Networks","created":"2016-12-31","cited_by_count":285},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"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":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"id":"1910.12638","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","created":"2019-10-25","cited_by_count":198},{"id":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"id":"2007.06028","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","created":"2020-07-12","cited_by_count":188},{"id":"1904.03240","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","created":"2019-04-05","cited_by_count":186},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"1910.06379","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","created":"2019-10-14","cited_by_count":182},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"2202.05256","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","created":"2022-02-10","cited_by_count":132},{"id":"1806.03185","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","created":"2018-06-08","cited_by_count":125},{"id":"1711.00541","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","created":"2017-11-01","cited_by_count":115},{"id":"1905.04874","title":"MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement","created":"2019-05-13","cited_by_count":104},{"id":"1703.06284","title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks","created":"2017-03-18","cited_by_count":98},{"id":"2002.08933","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","created":"2020-02-20","cited_by_count":75},{"id":"1810.04826","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","created":"2018-10-11","cited_by_count":73},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2007.13975","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","created":"2020-07-28","cited_by_count":68},{"id":"2107.11876","title":"A Study on Speech Enhancement Based on Diffusion Probabilistic Model","created":"2021-07-25","cited_by_count":53},{"id":"2007.06833","title":"Sudo rm -rf: Efficient Networks for Universal Audio Source Separation","created":"2020-07-14","cited_by_count":51},{"id":"1706.07162","title":"A Wavenet for Speech Denoising","created":"2017-06-22","cited_by_count":47},{"id":"2003.01531","title":"Voice Separation with an Unknown Number of Multiple Speakers","created":"2020-02-29","cited_by_count":46},{"id":"1607.02173","title":"Single-Channel Multi-Speaker Separation using Deep Clustering","created":"2016-07-07","cited_by_count":45},{"id":"2203.15149","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","created":"2022-03-28","cited_by_count":45},{"id":"2002.03921","title":"End-to-End Multi-speaker Speech Recognition with Transformer","created":"2020-02-10","cited_by_count":42},{"id":"2005.11138","title":"TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids","created":"2020-05-20","cited_by_count":42},{"id":"1905.03330","title":"Universal Sound Separation","created":"2019-05-08","cited_by_count":41},{"id":"2006.05694","title":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","created":"2020-06-10","cited_by_count":40},{"id":"1910.10942","title":"A Recurrent Variational Autoencoder for Speech Enhancement","created":"2019-10-24","cited_by_count":38},{"id":"2204.05841","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","created":"2022-04-12","cited_by_count":37},{"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":"2203.07960","title":"Investigating self-supervised learning for speech enhancement and separation","created":"2022-03-15","cited_by_count":35},{"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":"2112.02321","title":"Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network","created":"2021-12-04","cited_by_count":32},{"id":"2106.12271","title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","created":"2021-06-23","cited_by_count":28},{"id":"1611.08930","title":"Deep attractor network for single-microphone speaker separation","created":"2016-11-27","cited_by_count":26},{"id":"1709.03658","title":"End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks","created":"2017-09-12","cited_by_count":26},{"id":"1806.10522","title":"Speech Denoising with Deep Feature Losses","created":"2018-06-27","cited_by_count":26},{"id":"2204.03339","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","created":"2022-04-07","cited_by_count":24},{"id":"2008.04470","title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","created":"2020-08-11","cited_by_count":23},{"id":"2001.05532","title":"Improving GANs for Speech Enhancement","created":"2020-01-15","cited_by_count":22},{"id":"1502.04149","title":"Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation","created":"2015-02-13","cited_by_count":20},{"id":"1904.11148","title":"Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation","created":"2019-04-25","cited_by_count":20},{"id":"2202.08862","title":"RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing","created":"2022-02-17","cited_by_count":20},{"id":"1711.05747","title":"Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition","created":"2017-11-15","cited_by_count":19},{"id":"1810.12187","title":"End-to-end music source separation: is it possible in the waveform domain?","created":"2018-10-29","cited_by_count":19},{"id":"1909.01019","title":"On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement","created":"2019-09-03","cited_by_count":18},{"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":"1707.03634","title":"Speaker-independent Speech Separation with Deep Attractor Network","created":"2017-07-12","cited_by_count":17},{"id":"1910.09804","title":"Two-Step Sound Source Separation: Training on Learned Latent Targets","created":"2019-10-22","cited_by_count":17},{"id":"2205.11801","title":"SepIt: Approaching a Single Channel Speech Separation Bound","created":"2022-05-24","cited_by_count":16},{"id":"1807.07501","title":"Noise Adaptive Speech Enhancement using Domain Adversarial Training","created":"2018-07-19","cited_by_count":15},{"id":"1902.04891","title":"FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks","created":"2019-02-12","cited_by_count":15},{"id":"2006.02786","title":"Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR","created":"2020-06-04","cited_by_count":15},{"id":"2101.08625","title":"Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech","created":"2021-01-21","cited_by_count":15},{"id":"1904.03065","title":"Recursive speech separation for unknown number of speakers","created":"2019-04-05","cited_by_count":14},{"id":"1811.09010","title":"Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective","created":"2018-11-22","cited_by_count":13},{"id":"2202.07790","title":"Speech Denoising in the Waveform Domain with Self-Attention","created":"2022-02-15","cited_by_count":13},{"id":"1911.08895","title":"Demystifying TasNet: A Dissecting Approach","created":"2019-11-20","cited_by_count":12},{"id":"2104.08955","title":"Many-Speakers Single Channel Speech Separation with Optimal Permutation Training","created":"2021-04-18","cited_by_count":11},{"id":"2106.12743","title":"A Simultaneous Denoising and Dereverberation Framework with Target Decoupling","created":"2021-06-24","cited_by_count":11},{"id":"2206.09507","title":"Resource-Efficient Separation Transformer","created":"2022-06-19","cited_by_count":11},{"id":"1611.06265","title":"Deep Clustering and Conventional Networks for Music Separation: Stronger Together","created":"2016-11-18","cited_by_count":10},{"id":"2103.00819","title":"Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation","created":"2021-03-01","cited_by_count":10},{"id":"2206.11703","title":"Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes","created":"2022-06-23","cited_by_count":10},{"id":"2211.02542","title":"Self-Supervised Learning for Speech Enhancement through Synthesis","created":"2022-11-04","cited_by_count":10},{"id":"2106.07843","title":"Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation","created":"2021-06-15","cited_by_count":9},{"id":"2111.07578","title":"Monaural source separation: From anechoic to reverberant environments","created":"2021-11-15","cited_by_count":9},{"id":"2112.05036","title":"Domain Adaptation and Autoencoder Based Unsupervised Speech Enhancement","created":"2021-12-09","cited_by_count":9}],"next_cursor":"100"}