{"total":207,"rows":[{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344,"area":"diffusion"},{"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":"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":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2311.08355","title":"Mustango: Toward Controllable Text-to-Music Generation","created":"2023-11-14","cited_by_count":100,"area":"diffusion"},{"id":"2404.10301","title":"Long-form music generation with latent diffusion","created":"2024-04-16","cited_by_count":89,"area":"diffusion"},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82,"area":null},{"id":"2401.12179","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","created":"2024-01-22","cited_by_count":73,"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":"2402.10009","title":"Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion","created":"2024-02-15","cited_by_count":60,"area":"diffusion"},{"id":"2308.12770","title":"WavMark: Watermarking for Audio Generation","created":"2023-08-24","cited_by_count":50,"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":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"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":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2311.00613","title":"Controllable Music Production with Diffusion Models and Guidance Gradients","created":"2023-11-01","cited_by_count":29,"area":"diffusion"},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2406.06979","title":"AudioMarkBench: Benchmarking Robustness of Audio Watermarking","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2201.13055","title":"Nystr\\\"om Kernel Mean Embeddings","created":"2022-01-31","cited_by_count":22,"area":null},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22,"area":"diffusion"},{"id":"2503.16669","title":"Aligning Text-to-Music Evaluation with Human Preferences","created":"2025-03-20","cited_by_count":21,"area":"alignment"},{"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":"2102.03229","title":"Multi-Task Self-Supervised Pre-Training for Music Classification","created":"2021-02-05","cited_by_count":18,"area":null},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","cited_by_count":18,"area":"diffusion"},{"id":"2105.12395","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","created":"2021-05-26","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":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2106.06426","title":"Catch-A-Waveform: Learning to Generate Audio from a Single Short Example","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2211.14627","title":"Where to Pay Attention in Sparse Training for Feature Selection?","created":"2022-11-26","cited_by_count":15,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2506.19085","title":"Benchmarking Music Generation Models and Metrics via Human Preference Studies","created":"2025-06-23","cited_by_count":15,"area":null},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","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":"2306.13512","title":"DISCO-10M: A Large-Scale Music Dataset","created":"2023-06-23","cited_by_count":13,"area":null},{"id":"2410.05151","title":"Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer","created":"2024-10-07","cited_by_count":13,"area":"diffusion"},{"id":"2505.18186","title":"Discovering and Steering Interpretable Concepts in Large Generative Music Models","created":"2025-05-18","cited_by_count":13,"area":"mechinterp"},{"id":"2401.12238","title":"Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2406.07532","title":"Hearing Anything Anywhere","created":"2024-06-11","cited_by_count":12,"area":null},{"id":"2501.11311","title":"A2SB: Audio-to-Audio Schrodinger Bridges","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"area":null},{"id":"2106.06312","title":"A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2307.11078","title":"Brain2Music: Reconstructing Music from Human Brain Activity","created":"2023-07-20","cited_by_count":10,"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":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2103.17059","title":"Reliable Detection of Compressed and Encrypted Data","created":"2021-03-31","cited_by_count":8,"area":null},{"id":"2409.11264","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2110.10996","title":"Mean Nystr\\\"om Embeddings for Adaptive Compressive Learning","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2405.15863","title":"Quality-aware Masked Diffusion Transformer for Enhanced Music Generation","created":"2024-05-24","cited_by_count":6,"area":"diffusion"},{"id":"2506.00736","title":"IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling","created":"2025-05-31","cited_by_count":6,"area":"diffusion"},{"id":"2102.00201","title":"Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2207.04471","title":"Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation","created":"2022-07-10","cited_by_count":5,"area":null},{"id":"2307.09795","title":"From West to East: Who can understand the music of the others better?","created":"2023-07-19","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":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2311.03517","title":"SoundCam: A Dataset for Finding Humans Using Room Acoustics","created":"2023-11-06","cited_by_count":5,"area":null},{"id":"2402.09318","title":"Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2407.07275","title":"Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual Support","created":"2024-07-09","cited_by_count":5,"area":null},{"id":"2409.12634","title":"Exploring bat song syllable representations in self-supervised audio encoders","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2501.10807","title":"FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation","created":"2025-01-18","cited_by_count":5,"area":"diffusion"},{"id":"2502.04230","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2506.00681","title":"Learning to Upsample and Upmix Audio in the Latent Domain","created":"2025-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2508.11818","title":"Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound Understanding","created":"2025-08-15","cited_by_count":5,"area":"lr"},{"id":"2509.23727","title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2511.13300","title":"PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2601.16483","title":"FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning","created":"2026-01-23","cited_by_count":5,"area":"diffusion"},{"id":"2203.12798","title":"DPar2: Fast and Scalable PARAFAC2 Decomposition for Irregular Dense Tensors","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2409.09601","title":"A Survey of Foundation Models for Music Understanding","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2504.00837","title":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2504.13535","title":"MusFlow: Multimodal Music Generation via Conditional Flow Matching","created":"2025-04-18","cited_by_count":4,"area":"diffusion"},{"id":"2505.23305","title":"MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction","created":"2025-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2507.12042","title":"Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2509.14912","title":"Back to Ear: Perceptually Driven High Fidelity Music Reconstruction","created":"2025-09-18","cited_by_count":4,"area":"diffusion"},{"id":"2510.13344","title":"UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE","created":"2025-10-15","cited_by_count":4,"area":"moe"},{"id":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2606.17006","title":"TuneJury: An Open Metric for Improving Music Generation Preference Alignment","created":"2026-06-15","cited_by_count":4,"area":"alignment"},{"id":"2111.06458","title":"MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification","created":"2021-11-11","cited_by_count":3,"area":null},{"id":"2211.08379","title":"Music Instrument Classification Reprogrammed","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2211.11060","title":"Simultaneously Learning Robust Audio Embeddings and balanced Hash codes for Query-by-Example","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2302.08632","title":"jazznet: A Dataset of Fundamental Piano Patterns for Music Audio Machine Learning Research","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2309.15717","title":"Timbre-Trap: A Low-Resource Framework for Instrument-Agnostic Music Transcription","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2310.05799","title":"The First Cadenza Signal Processing Challenge: Improving Music for Those With a Hearing Loss","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2312.09207","title":"WikiMuTe: A web-sourced dataset of semantic descriptions for music audio","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2401.01145","title":"HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing Aids","created":"2024-01-02","cited_by_count":3,"area":null},{"id":"2407.08647","title":"From Real to Cloned Singer Identification","created":"2024-07-11","cited_by_count":3,"area":null},{"id":"2410.13114","title":"Sound Check: Auditing Audio Datasets","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2501.14680","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","created":"2025-01-24","cited_by_count":3,"area":"diffusion"},{"id":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2510.00771","title":"UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching","created":"2025-10-01","cited_by_count":3,"area":"diffusion"},{"id":"2511.21577","title":"HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal","created":"2025-11-26","cited_by_count":3,"area":null}],"next_cursor":"100"}