{"total":225,"rows":[{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"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":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156,"area":"lr"},{"id":"2103.16091","title":"Symbolic Music Generation with Diffusion Models","created":"2021-03-30","cited_by_count":154,"area":"diffusion"},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","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":"2111.05011","title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","created":"2021-11-09","cited_by_count":73,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2111.06387","title":"Learning Signal-Agnostic Manifolds of Neural Fields","created":"2021-11-11","cited_by_count":45,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","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":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2204.07172","title":"Diagnosing and Fixing Manifold Overfitting in Deep Generative Models","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26,"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":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2208.08706","title":"Musika! Fast Infinite Waveform Music Generation","created":"2022-08-18","cited_by_count":24,"area":null},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","cited_by_count":18,"area":null},{"id":"2310.19180","title":"JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation","created":"2023-10-29","cited_by_count":17,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2106.05838","title":"Large-scale optimal transport map estimation using projection pursuit","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2209.00130","title":"Evaluating generative audio systems and their metrics","created":"2022-08-31","cited_by_count":16,"area":null},{"id":"2110.03485","title":"Cartoon Explanations of Image Classifiers","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2112.04214","title":"Learning music audio representations via weak language supervision","created":"2021-12-08","cited_by_count":13,"area":null},{"id":"2204.12076","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","created":"2022-04-26","cited_by_count":13,"area":"distill"},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2107.02621","title":"Energy Consumption of Deep Generative Audio Models","created":"2021-07-06","cited_by_count":12,"area":null},{"id":"2107.05050","title":"Neural Waveshaping Synthesis","created":"2021-07-11","cited_by_count":12,"area":null},{"id":"2202.06034","title":"Deep Performer: Score-to-Audio Music Performance Synthesis","created":"2022-02-12","cited_by_count":12,"area":null},{"id":"2211.01839","title":"HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2102.04680","title":"Tr\\\"aumerAI: Dreaming Music with StyleGAN","created":"2021-02-09","cited_by_count":11,"area":null},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","cited_by_count":11,"area":null},{"id":"2110.08252","title":"A Rate-Distortion Framework for Explaining Black-box Model Decisions","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2210.06007","title":"JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2211.09124","title":"A Review of Intelligent Music Generation Systems","created":"2022-11-16","cited_by_count":11,"area":null},{"id":"2302.04959","title":"Hypernetworks build Implicit Neural Representations of Sounds","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2501.11311","title":"A2SB: Audio-to-Audio Schrodinger Bridges","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2503.00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","created":"2025-02-28","cited_by_count":11,"area":"diffusion"},{"id":"2106.06410","title":"What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2206.12038","title":"BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping","created":"2022-06-24","cited_by_count":10,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2106.00992","title":"NVC-Net: End-to-End Adversarial Voice Conversion","created":"2021-06-02","cited_by_count":9,"area":null},{"id":"2201.02490","title":"Audio representations for deep learning in sound synthesis: A review","created":"2022-01-07","cited_by_count":9,"area":null},{"id":"2211.05385","title":"GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning","created":"2022-11-10","cited_by_count":9,"area":null},{"id":"2308.12982","title":"A Survey of AI Music Generation Tools and Models","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2312.14507","title":"Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport","created":"2023-12-22","cited_by_count":8,"area":null},{"id":"2408.02514","title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2409.19806","title":"PALM: Few-Shot Prompt Learning for Audio Language Models","created":"2024-09-29","cited_by_count":8,"area":"mllm"},{"id":"2506.10488","title":"Sheet Music Benchmark: Standardized Optical Music Recognition Evaluation","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2102.06306","title":"DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals","created":"2021-02-11","cited_by_count":7,"area":null},{"id":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"area":null},{"id":"2307.04586","title":"Timbre transfer using image-to-image denoising diffusion implicit models","created":"2023-07-10","cited_by_count":7,"area":"diffusion"},{"id":"2308.13736","title":"A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music","created":"2023-08-26","cited_by_count":7,"area":null},{"id":"2401.12570","title":"DiffMoog: a Differentiable Modular Synthesizer for Sound Matching","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2408.06022","title":"Controlling Surprisal in Music Generation via Information Content Curve Matching","created":"2024-08-12","cited_by_count":7,"area":null},{"id":"2104.02656","title":"Collaborative Learning to Generate Audio-Video Jointly","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6,"area":null},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2402.08300","title":"An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2506.07199","title":"Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching","created":"2025-06-08","cited_by_count":6,"area":"diffusion"},{"id":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2108.01216","title":"DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs","created":"2021-08-03","cited_by_count":5,"area":"distill"},{"id":"2109.02823","title":"Learning Visual-Audio Representations for Voice-Controlled Robots","created":"2021-09-07","cited_by_count":5,"area":null},{"id":"2111.08462","title":"Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations","created":"2021-11-14","cited_by_count":5,"area":null},{"id":"2202.05068","title":"Controlling the Complexity and Lipschitz Constant improves polynomial nets","created":"2022-02-10","cited_by_count":5,"area":null},{"id":"2211.11225","title":"TimbreCLIP: Connecting Timbre to Text and Images","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2307.05161","title":"On the Effectiveness of Speech Self-supervised Learning for Music","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2309.12283","title":"Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis","created":"2023-09-21","cited_by_count":5,"area":null},{"id":"2401.13498","title":"Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting","created":"2024-01-24","cited_by_count":5,"area":null},{"id":"2402.15569","title":"Toward Fully Self-Supervised Multi-Pitch Estimation","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2502.08939","title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2110.05941","title":"Rank-based loss for learning hierarchical representations","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2111.10003","title":"Differentiable Wavetable Synthesis","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2112.03163","title":"Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization","created":"2021-12-06","cited_by_count":4,"area":null}],"next_cursor":"100"}