{"total":139,"rows":[{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"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":"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":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"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":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"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":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"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":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2209.14275","title":"Audio Retrieval with WavText5K and CLAP Training","created":"2022-09-28","cited_by_count":35,"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":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"area":null},{"id":"2311.05152","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","created":"2023-11-09","cited_by_count":31,"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":"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":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2308.04978","title":"Transferable Models for Bioacoustics with Human Language Supervision","created":"2023-08-09","cited_by_count":21,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2502.06710","title":"Learning Musical Representations for Music Performance Question Answering","created":"2025-02-10","cited_by_count":17,"area":null},{"id":"2302.14638","title":"SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2309.10667","title":"Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"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":"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":"2312.10144","title":"Data-Efficient Multimodal Fusion on a Single GPU","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2407.15060","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","created":"2024-07-21","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":"2405.10084","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2503.12840","title":"Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics","created":"2025-03-17","cited_by_count":9,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2503.12847","title":"Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2302.05940","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2402.02694","title":"Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2501.09291","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","created":"2025-01-16","cited_by_count":7,"area":null},{"id":"2311.11375","title":"ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2023-11-19","cited_by_count":6,"area":null},{"id":"2406.07012","title":"Bridging Language Gaps in Audio-Text Retrieval","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2506.01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","created":"2025-06-01","cited_by_count":6,"area":null},{"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":"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":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2307.09286","title":"FlexiAST: Flexibility is What AST Needs","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2311.04339","title":"InstrumentGen: Generating Sample-Based Musical Instruments From Text","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2405.03952","title":"HAFFormer: A Hierarchical Attention-Free Framework for Alzheimer's Disease Detection From Spontaneous Speech","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2406.00294","title":"Creative Text-to-Audio Generation via Synthesizer Programming","created":"2024-06-01","cited_by_count":4,"area":null},{"id":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2408.10998","title":"Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2507.14935","title":"Open-set Cross Modal Generalization via Multimodal Unified Representation","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2604.01929","title":"Woosh: A Sound Effects Foundation Model","created":"2026-04-02","cited_by_count":4,"area":null},{"id":"2210.11328","title":"Play It Back: Iterative Attention for Audio Recognition","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2302.08639","title":"Improving Transformer-based Networks With Locality For Automatic Speaker Verification","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2305.00104","title":"MMViT: Multiscale Multiview Vision Transformers","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2409.11498","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2411.15685","title":"State-Space Large Audio Language Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2502.10718","title":"Hyperdimensional Intelligent Sensing for Efficient Real-Time Audio Processing on Extreme Edge","created":"2025-02-15","cited_by_count":3,"area":null},{"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":"2508.03724","title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2512.20117","title":"Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2303.05678","title":"Improving Weakly Supervised Sound Event Detection with Causal Intervention","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2410.07277","title":"Swin-BERT: A Feature Fusion System designed for Speech-based Alzheimer's Dementia Detection","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2512.00115","title":"MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2206.11260","title":"Few-shot Long-Tailed Bird Audio Recognition","created":"2022-06-22","cited_by_count":1,"area":null},{"id":"2211.12195","title":"Ontology-aware Learning and Evaluation for Audio Tagging","created":"2022-11-22","cited_by_count":1,"area":null},{"id":"2308.07221","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2309.14460","title":"Online Active Learning For Sound Event Detection","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2401.08415","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2401.10544","title":"AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks","created":"2024-01-19","cited_by_count":1,"area":null},{"id":"2406.03272","title":"Multi-Microphone Speech Emotion Recognition using the Hierarchical Token-semantic Audio Transformer Architecture","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2407.15641","title":"Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2410.12028","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2412.17306","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2501.12796","title":"Hybrid Losses for Hierarchical Embedding Learning","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2502.05435","title":"Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2502.12925","title":"Keep what you need : extracting efficient subnetworks from large audio representation models","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2507.21588","title":"Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2509.12591","title":"MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.25495","title":"EMO-TTA: Improving Test-Time Adaptation of Audio-Language Models for Speech Emotion Recognition","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2512.02206","title":"WhAM: Towards A Translative Model of Sperm Whale Vocalization","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2603.22053","title":"AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.03806","title":"Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2609.21183","title":"I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2302.03533","title":"Revisiting Pre-training in Audio-Visual Learning","created":"2023-02-07","cited_by_count":0,"area":null}],"next_cursor":"100"}