{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"1911.07023","title":"Effectively Unbiased FID and Inception Score and where to find them","created":"2019-11-16","cited_by_count":165},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2404.09956","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","created":"2024-04-15","cited_by_count":97},{"id":"2211.03089","title":"I Hear Your True Colors: Image Guided Audio Generation","created":"2022-11-06","cited_by_count":92},{"id":"2311.01616","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","created":"2023-11-02","cited_by_count":92},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65},{"id":"2401.01044","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","created":"2024-01-02","cited_by_count":54},{"id":"2409.13689","title":"Temporally Aligned Audio for Video with Autoregression","created":"2024-09-20","cited_by_count":52},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48},{"id":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","cited_by_count":42},{"id":"2309.10537","title":"FoleyGen: Visually-Guided Audio Generation","created":"2023-09-19","cited_by_count":40},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34},{"id":"2406.08384","title":"Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models","created":"2024-06-12","cited_by_count":33},{"id":"2409.10819","title":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","created":"2024-09-17","cited_by_count":31},{"id":"2412.17667","title":"VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music","created":"2024-12-23","cited_by_count":30},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28},{"id":"2310.15247","title":"SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis","created":"2023-10-23","cited_by_count":24},{"id":"2309.10740","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","created":"2023-09-19","cited_by_count":22},{"id":"2306.09635","title":"CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models","created":"2023-06-16","cited_by_count":20},{"id":"2304.12521","title":"Foley Sound Synthesis at the DCASE 2023 Challenge","created":"2023-04-25","cited_by_count":19},{"id":"2401.09294","title":"T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis","created":"2024-01-17","cited_by_count":19},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19},{"id":"2408.11915","title":"Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound","created":"2024-08-21","cited_by_count":16},{"id":"2410.05167","title":"Presto! Distilling Steps and Layers for Accelerating Music Generation","created":"2024-10-07","cited_by_count":16},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16},{"id":"2403.17508","title":"Correlation of Fr\\'echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant","created":"2024-03-26","cited_by_count":15},{"id":"2006.09266","title":"Comparing Representations for Audio Synthesis Using Generative Adversarial Networks","created":"2020-06-16","cited_by_count":14},{"id":"2410.17589","title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation","created":"2024-10-23","cited_by_count":6},{"id":"2305.15905","title":"Latent Diffusion Model Based Foley Sound Generation System For DCASE Challenge 2023 Task 7","created":"2023-05-25","cited_by_count":4},{"id":"2306.05004","title":"VIFS: An End-to-End Variational Inference for Foley Sound Synthesis","created":"2023-06-08","cited_by_count":2},{"id":"2404.00775","title":"Measuring Audio Prompt Adherence with Distribution-based Embedding Distances","created":"2024-03-31","cited_by_count":2},{"id":"2501.08587","title":"Sound Scene Synthesis at the DCASE 2024 Challenge","created":"2025-01-15","cited_by_count":2}],"next_cursor":null}