{"total":342,"rows":[{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"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":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213,"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":"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":"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":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"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":"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":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"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":"2205.03433","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","created":"2022-05-06","cited_by_count":62,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"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":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41,"area":null},{"id":"2404.02677","title":"The VoicePrivacy 2024 Challenge Evaluation Plan","created":"2024-04-03","cited_by_count":41,"area":null},{"id":"2504.04953","title":"M-Prometheus: A Suite of Open Multilingual LLM Judges","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34,"area":null},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","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":"2211.13929","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","created":"2022-11-25","cited_by_count":31,"area":"distill"},{"id":"2501.11378","title":"Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio","created":"2025-01-20","cited_by_count":31,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","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":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2204.02121","title":"MetaAudio: A Few-Shot Audio Classification Benchmark","created":"2022-04-05","cited_by_count":24,"area":null},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"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":"2501.15417","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","created":"2025-01-26","cited_by_count":23,"area":null},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22,"area":null},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22,"area":null},{"id":"2510.07293","title":"AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs","created":"2025-10-08","cited_by_count":22,"area":"inference"},{"id":"2507.08557","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2202.08862","title":"RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing","created":"2022-02-17","cited_by_count":20,"area":null},{"id":"2204.07554","title":"Efficient Architecture Search for Diverse Tasks","created":"2022-04-15","cited_by_count":18,"area":null},{"id":"2406.04350","title":"Prompt-guided Precise Audio Editing with Diffusion Models","created":"2024-05-11","cited_by_count":18,"area":"diffusion"},{"id":"2203.16104","title":"Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation","created":"2022-03-30","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":"2110.14131","title":"Temporal Knowledge Distillation for On-device Audio Classification","created":"2021-10-27","cited_by_count":15,"area":"distill"},{"id":"2402.16998","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","created":"2024-02-26","cited_by_count":15,"area":null},{"id":"2403.02522","title":"HeAR -- Health Acoustic Representations","created":"2024-03-04","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":"2403.11827","title":"Sound Event Detection and Localization with Distance Estimation","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2503.01725","title":"HarmonySet: A Comprehensive Dataset for Understanding Video-Music Semantic Alignment and Temporal Synchronization","created":"2025-03-03","cited_by_count":14,"area":null},{"id":"2508.18240","title":"MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols","created":"2025-08-22","cited_by_count":14,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14,"area":null},{"id":"2409.05929","title":"M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture","created":"2024-09-09","cited_by_count":13,"area":"moe"},{"id":"2508.15882","title":"Beyond Transcription: Mechanistic Interpretability in ASR","created":"2025-08-21","cited_by_count":13,"area":"mechinterp"},{"id":"2203.06760","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","created":"2022-03-13","cited_by_count":12,"area":"distill"},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"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":"2403.09502","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","created":"2024-03-14","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":"2509.21625","title":"Guiding Audio Editing with Audio Language Model","created":"2025-09-25","cited_by_count":12,"area":"diffusion"},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","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":"2505.14518","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2508.01277","title":"Foundation Models for Bioacoustics -- a Comparative Review","created":"2025-08-02","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":"2202.10372","title":"L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment","created":"2022-02-21","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":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2104.05499","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","created":"2021-04-12","cited_by_count":9,"area":null},{"id":"2305.09690","title":"A Whisper transformer for audio captioning trained with synthetic captions and transfer learning","created":"2023-05-15","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":"2403.05010","title":"RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction","created":"2024-03-08","cited_by_count":9,"area":"diffusion"},{"id":"2501.05987","title":"Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2602.07143","title":"Massive Sound Embedding Benchmark (MSEB)","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2104.13620","title":"IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2105.04727","title":"Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data","created":"2021-05-11","cited_by_count":8,"area":null},{"id":"2204.01851","title":"Dual Quaternion Ambisonics Array for Six-Degree-of-Freedom Acoustic Representation","created":"2022-04-04","cited_by_count":8,"area":null},{"id":"2207.09514","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2210.12108","title":"Adversarial Permutation Invariant Training for Universal Sound Separation","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2409.11145","title":"High-Resolution Speech Restoration with Latent Diffusion Model","created":"2024-09-17","cited_by_count":8,"area":"diffusion"},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2601.11846","title":"The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymization","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2602.05027","title":"AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders","created":"2026-02-04","cited_by_count":8,"area":"mechinterp"},{"id":"2604.19300","title":"HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models","created":"2026-04-21","cited_by_count":8,"area":null},{"id":"2107.10716","title":"Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough","created":"2021-07-12","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":"2210.07978","title":"Improving generalizability of distilled self-supervised speech processing models under distorted settings","created":"2022-10-14","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2404.16436","title":"Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics","created":"2024-04-25","cited_by_count":7,"area":null},{"id":"2406.10254","title":"Towards Signal Processing In Large Language Models","created":"2024-06-10","cited_by_count":7,"area":null}],"next_cursor":"100"}