{"total":574,"rows":[{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643,"area":null},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599,"area":"diffusion"},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2303.13874","title":"Query-Dependent Video Representation for Moment Retrieval and Highlight Detection","created":"2023-03-24","cited_by_count":166,"area":null},{"id":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157,"area":null},{"id":"2203.12745","title":"UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection","created":"2022-03-23","cited_by_count":148,"area":null},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"area":null},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134,"area":"diffusion"},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120,"area":"diffusion"},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100,"area":"diffusion"},{"id":"2308.01546","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","created":"2023-08-03","cited_by_count":94,"area":"diffusion"},{"id":"2305.18474","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","created":"2023-05-29","cited_by_count":90,"area":"diffusion"},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2304.00830","title":"AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models","created":"2023-04-03","cited_by_count":83,"area":"diffusion"},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83,"area":null},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"area":null},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78,"area":"diffusion"},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"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,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2401.02309","title":"TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2107.09817","title":"Audio Captioning Transformer","created":"2021-07-21","cited_by_count":55,"area":null},{"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,"area":"diffusion"},{"id":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46,"area":"diffusion"},{"id":"2305.06908","title":"CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model","created":"2023-05-11","cited_by_count":45,"area":"diffusion"},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40,"area":"diffusion"},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39,"area":null},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37,"area":"ssm"},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"area":null},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2506.21448","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","created":"2025-06-26","cited_by_count":34,"area":"lr"},{"id":"2110.04684","title":"Can Audio Captions Be Evaluated with Image Caption Metrics?","created":"2021-10-10","cited_by_count":33,"area":null},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33,"area":null},{"id":"2112.09312","title":"MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling","created":"2021-12-17","cited_by_count":32,"area":null},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2409.10819","title":"EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer","created":"2024-09-17","cited_by_count":31,"area":"diffusion"},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30,"area":null},{"id":"2308.11957","title":"CED: Consistent ensemble distillation for audio tagging","created":"2023-08-23","cited_by_count":29,"area":"distill"},{"id":"2312.00083","title":"BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos","created":"2023-11-30","cited_by_count":29,"area":null},{"id":"2401.17690","title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","created":"2024-01-31","cited_by_count":28,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27,"area":null},{"id":"2211.04772","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","created":"2022-11-09","cited_by_count":27,"area":"distill"},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2309.08051","title":"Retrieval-Augmented Text-to-Audio Generation","created":"2023-09-14","cited_by_count":24,"area":"rag"},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22,"area":null},{"id":"2309.10740","title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","created":"2023-09-19","cited_by_count":22,"area":"diffusion"},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2306.01433","title":"Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach","created":"2023-06-02","cited_by_count":21,"area":null},{"id":"2409.07614","title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","created":"2024-09-11","cited_by_count":21,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19,"area":"diffusion"},{"id":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2203.02838","title":"Leveraging Pre-trained BERT for Audio Captioning","created":"2022-03-06","cited_by_count":18,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2308.11940","title":"Audio Generation with Multiple Conditional Diffusion Model","created":"2023-08-23","cited_by_count":18,"area":"diffusion"},{"id":"2402.03951","title":"Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping","created":"2024-02-06","cited_by_count":18,"area":null},{"id":"2103.08310","title":"EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognition","created":"2021-03-10","cited_by_count":17,"area":null},{"id":"2203.16930","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","created":"2022-03-31","cited_by_count":17,"area":null},{"id":"2305.14579","title":"Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning","created":"2023-05-23","cited_by_count":17,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null}],"next_cursor":"100"}