{"list":"other","total":118,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","created":"2019-02-11","cited_by_count":267},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"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":"2001.04643","title":"DDSP: Differentiable Digital Signal Processing","created":"2020-01-14","cited_by_count":178},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"1901.05335","title":"A review of domain adaptation without target labels","created":"2019-01-16","cited_by_count":156},{"id":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2012.08405","title":"Model-Based Deep Learning","created":"2020-12-15","cited_by_count":141},{"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":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"id":"1907.12740","title":"Deep Learning in Video Multi-Object Tracking: A Survey","created":"2019-07-18","cited_by_count":107},{"id":"1905.00078","title":"Deep Learning for Audio Signal Processing","created":"2019-04-30","cited_by_count":92},{"id":"1608.04363","title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","created":"2016-08-15","cited_by_count":85},{"id":"1807.00129","title":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","created":"2018-06-30","cited_by_count":85},{"id":"1701.01909","title":"Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies","created":"2017-01-08","cited_by_count":76},{"id":"1810.06682","title":"Trellis Networks for Sequence Modeling","created":"2018-10-15","cited_by_count":52},{"id":"1810.11359","title":"gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Acceleration","created":"2018-10-26","cited_by_count":46},{"id":"1811.06795","title":"Building and Evaluation of a Real Room Impulse Response Dataset","created":"2018-11-16","cited_by_count":43},{"id":"1911.09033","title":"Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking","created":"2019-11-20","cited_by_count":40},{"id":"1905.04418","title":"Machine learning in acoustics: theory and applications","created":"2019-05-11","cited_by_count":36},{"id":"2012.02337","title":"Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking","created":"2020-12-03","cited_by_count":36},{"id":"2001.05425","title":"UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking","created":"2020-01-15","cited_by_count":34},{"id":"2006.02609","title":"Simple Unsupervised Multi-Object Tracking","created":"2020-06-04","cited_by_count":33},{"id":"1910.14104","title":"End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation","created":"2019-10-30","cited_by_count":31},{"id":"2009.02792","title":"Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019","created":"2020-09-06","cited_by_count":31},{"id":"1703.01789","title":"Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms","created":"2017-03-06","cited_by_count":27},{"id":"1710.10059","title":"Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network","created":"2017-10-27","cited_by_count":27},{"id":"2010.15306","title":"ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection","created":"2020-10-29","cited_by_count":26},{"id":"2010.13092","title":"An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection","created":"2020-10-25","cited_by_count":25},{"id":"1711.11565","title":"Deep Neural Networks for Multiple Speaker Detection and Localization","created":"2017-11-30","cited_by_count":23},{"id":"1809.03137","title":"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers","created":"2018-09-10","cited_by_count":22},{"id":"1806.07789","title":"Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition","created":"2018-06-20","cited_by_count":21},{"id":"2006.01919","title":"A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection","created":"2020-06-02","cited_by_count":21},{"id":"2010.06007","title":"The Cone of Silence: Speech Separation by Localization","created":"2020-10-12","cited_by_count":21},{"id":"2101.02919","title":"A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection","created":"2021-01-08","cited_by_count":21},{"id":"2106.06999","title":"A Dataset of Dynamic Reverberant Sound Scenes with Directional Interferers for Sound Event Localization and Detection","created":"2021-06-13","cited_by_count":21},{"id":"1805.02410","title":"MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation","created":"2018-05-07","cited_by_count":19},{"id":"1905.00268","title":"Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy","created":"2019-05-01","cited_by_count":19},{"id":"1812.06811","title":"Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events","created":"2018-12-17","cited_by_count":18},{"id":"1905.08546","title":"A multi-room reverberant dataset for sound event localization and detection","created":"2019-05-21","cited_by_count":18},{"id":"1909.01008","title":"The LOCATA Challenge: Acoustic Source Localization and Tracking","created":"2019-09-03","cited_by_count":17},{"id":"1705.00919","title":"Broadband DOA estimation using Convolutional neural networks trained with noise signals","created":"2017-05-02","cited_by_count":15},{"id":"2006.09006","title":"Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks","created":"2020-06-16","cited_by_count":15},{"id":"1811.06713","title":"Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization","created":"2018-11-16","cited_by_count":14},{"id":"2102.07955","title":"Deep Learning based Multi-Source Localization with Source Splitting and its Effectiveness in Multi-Talker Speech Recognition","created":"2021-02-16","cited_by_count":14},{"id":"1912.04357","title":"DeepMUSIC: Multiple Signal Classification via Deep Learning","created":"2019-12-09","cited_by_count":13},{"id":"1910.04388","title":"First Order Ambisonics Domain Spatial Augmentation for DNN-based Direction of Arrival Estimation","created":"2019-10-10","cited_by_count":12},{"id":"1807.11094","title":"Towards End-to-End Acoustic Localization using Deep Learning: from Audio Signal to Source Position Coordinates","created":"2018-07-29","cited_by_count":11},{"id":"1711.08016","title":"Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition","created":"2017-11-21","cited_by_count":10},{"id":"1807.11722","title":"Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals","created":"2018-07-31","cited_by_count":10},{"id":"1904.12769","title":"Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network","created":"2019-04-29","cited_by_count":10},{"id":"2002.05865","title":"A Sequence Matching Network for Polyphonic Sound Event Localization and Detection","created":"2020-02-14","cited_by_count":10},{"id":"2010.00140","title":"Event-Independent Network for Polyphonic Sound Event Localization and Detection","created":"2020-09-30","cited_by_count":9},{"id":"2104.05499","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","created":"2021-04-12","cited_by_count":9},{"id":"2106.10801","title":"MeshRIR: A Dataset of Room Impulse Responses on Meshed Grid Points For Evaluating Sound Field Analysis and Synthesis Methods","created":"2021-06-21","cited_by_count":9},{"id":"1908.00766","title":"Sound source detection, localization and classification using consecutive ensemble of CRNN models","created":"2019-08-02","cited_by_count":8},{"id":"2007.13976","title":"Self-supervised Neural Audio-Visual Sound Source Localization via Probabilistic Spatial Modeling","created":"2020-07-28","cited_by_count":8},{"id":"2011.00091","title":"Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization","created":"2020-10-30","cited_by_count":8},{"id":"2106.06969","title":"SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform","created":"2021-06-13","cited_by_count":8},{"id":"2002.05994","title":"Sound Event Localization based on Sound Intensity Vector Refined By DNN-Based Denoising and Source Separation","created":"2020-02-14","cited_by_count":7},{"id":"2005.13163","title":"Semi-supervised source localization with deep generative modeling","created":"2020-05-27","cited_by_count":7},{"id":"2106.03903","title":"PILOT: Introducing Transformers for Probabilistic Sound Event Localization","created":"2021-06-07","cited_by_count":7},{"id":"2107.09388","title":"Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection","created":"2021-07-20","cited_by_count":7},{"id":"1904.01916","title":"End-to-end Binaural Sound Localisation from the Raw Waveform","created":"2019-04-03","cited_by_count":6},{"id":"1904.03476","title":"Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems","created":"2019-04-06","cited_by_count":6},{"id":"2012.03574","title":"Reverberant Sound Localization with a Robot Head Based on Direct-Path Relative Transfer Function","created":"2020-12-07","cited_by_count":6},{"id":"2103.00417","title":"Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization","created":"2021-02-28","cited_by_count":6},{"id":"1808.06429","title":"Deep Residual Network for Sound Source Localization in the Time Domain","created":"2018-08-20","cited_by_count":5},{"id":"1904.08452","title":"Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural Networks","created":"2019-04-17","cited_by_count":5},{"id":"2003.01609","title":"SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks","created":"2020-03-03","cited_by_count":5},{"id":"2011.07859","title":"A General Network Architecture for Sound Event Localization and Detection Using Transfer Learning and Recurrent Neural Network","created":"2020-11-16","cited_by_count":5},{"id":"2101.10636","title":"Semi-supervised source localization in reverberant environments with deep generative modeling","created":"2021-01-26","cited_by_count":5},{"id":"2105.01897","title":"Improved feature extraction for CRNN-based multiple sound source localization","created":"2021-05-05","cited_by_count":5},{"id":"2106.10806","title":"Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection","created":"2021-06-21","cited_by_count":5},{"id":"1712.04276","title":"Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise","created":"2017-12-12","cited_by_count":4},{"id":"1902.03569","title":"Performance Advantages of Deep Neural Networks for Angle of Arrival Estimation","created":"2019-02-10","cited_by_count":4},{"id":"2002.00641","title":"Time Difference of Arrival Estimation from Frequency-Sliding Generalized Cross-Correlations Using Convolutional Neural Networks","created":"2020-02-03","cited_by_count":4},{"id":"2006.12014","title":"Sound Event Localization and Detection Using Activity-Coupled Cartesian DOA Vector and RD3net","created":"2020-06-22","cited_by_count":4},{"id":"2012.05533","title":"Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization","created":"2020-12-10","cited_by_count":4},{"id":"2107.11066","title":"SALADnet: Self-Attentive multisource Localization in the Ambisonics Domain","created":"2021-07-23","cited_by_count":4},{"id":"1810.04080","title":"TRAMP: Tracking by a Real-time AMbisonic-based Particle filter","created":"2018-10-09","cited_by_count":3},{"id":"2003.07839","title":"High-Resolution Speaker Counting In Reverberant Rooms Using CRNN With Ambisonics Features","created":"2020-03-17","cited_by_count":3}],"next_cursor":"100"}