{"list":"other","total":56,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"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":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2301.02379","title":"CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior","created":"2023-01-06","cited_by_count":184},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2302.03917","title":"Noise2Music: Text-conditioned Music Generation with Diffusion Models","created":"2023-02-08","cited_by_count":173},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"1810.11846","title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","created":"2018-10-28","cited_by_count":110},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2102.06837","title":"Learning Speech-driven 3D Conversational Gestures from Video","created":"2021-02-13","cited_by_count":98},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2207.11243","title":"Multiface: A Dataset for Neural Face Rendering","created":"2022-07-22","cited_by_count":87},{"id":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78},{"id":"2006.03575","title":"End-to-End Adversarial Text-to-Speech","created":"2020-06-05","cited_by_count":77},{"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":"2401.04747","title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","created":"2024-01-09","cited_by_count":62},{"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":"2201.07429","title":"Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis","created":"2022-01-19","cited_by_count":53},{"id":"1509.08062","title":"End-to-End Text-Dependent Speaker Verification","created":"2015-09-27","cited_by_count":49},{"id":"2007.04590","title":"DeepSinger: Singing Voice Synthesis with Data Mined From the Web","created":"2020-07-09","cited_by_count":32},{"id":"2312.10741","title":"StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis","created":"2023-12-17","cited_by_count":21},{"id":"2012.00337","title":"NHSS: A Speech and Singing Parallel Database","created":"2020-12-01","cited_by_count":16},{"id":"2001.07044","title":"JVS-MuSiC: Japanese multispeaker singing-voice corpus","created":"2020-01-20","cited_by_count":14},{"id":"2305.10686","title":"RMSSinger: Realistic-Music-Score based Singing Voice Synthesis","created":"2023-05-18","cited_by_count":12},{"id":"2303.12822","title":"Co-Speech Gesture Synthesis using Discrete Gesture Token Learning","created":"2023-03-04","cited_by_count":9},{"id":"2203.10750","title":"WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses","created":"2022-03-21","cited_by_count":7},{"id":"2203.00931","title":"MuSE-SVS: Multi-Singer Emotional Singing Voice Synthesizer that Controls Emotional Intensity","created":"2022-03-02","cited_by_count":6}],"next_cursor":null}