{"total":39,"rows":[{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2306.00956","title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","created":"2023-06-01","cited_by_count":41,"area":null},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2210.09304","title":"Non-Contrastive Learning Meets Language-Image Pre-Training","created":"2022-10-17","cited_by_count":25,"area":null},{"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":"2401.08053","title":"SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation","created":"2024-01-16","cited_by_count":19,"area":null},{"id":"2306.00349","title":"CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2306.12957","title":"Siamese SIREN: Audio Compression with Implicit Neural Representations","created":"2023-06-22","cited_by_count":13,"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":"2204.13289","title":"Music Enhancement via Image Translation and Vocoding","created":"2022-04-28","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":"2206.12559","title":"Self-supervised Context-aware Style Representation for Expressive Speech Synthesis","created":"2022-06-25","cited_by_count":10,"area":null},{"id":"2209.01478","title":"Equivariant Self-Supervision for Musical Tempo Estimation","created":"2022-09-03","cited_by_count":9,"area":null},{"id":"2306.09944","title":"RealImpact: A Dataset of Impact Sound Fields for Real Objects","created":"2023-06-16","cited_by_count":9,"area":null},{"id":"2410.05920","title":"FINALLY: fast and universal speech enhancement with studio-like quality","created":"2024-10-08","cited_by_count":7,"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":"2311.16535","title":"Contrastive encoder pre-training-based clustered federated learning for heterogeneous data","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2502.12759","title":"High-Fidelity Music Vocoder using Neural Audio Codecs","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2203.04444","title":"Reproducible Subjective Evaluation","created":"2022-03-08","cited_by_count":2,"area":null},{"id":"2211.06646","title":"Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2306.01442","title":"Towards Robust FastSpeech 2 by Modelling Residual Multimodality","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2401.07957","title":"Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2412.09405","title":"Learned Compression for Compressed Learning","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2506.09989","title":"Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2209.11003","title":"Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2210.05513","title":"ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2305.11582","title":"What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2310.09388","title":"CORN: Co-Trained Full- And No-Reference Speech Quality Assessment","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2507.11636","title":"JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2601.19702","title":"SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2605.03929","title":"PHALAR: Phasors for Learned Musical Audio Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2304.07449","title":"Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging","created":"2023-04-15","cited_by_count":0,"area":null},{"id":"2409.15545","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2503.02585","title":"As Good as It KAN Get: High-Fidelity Audio Representation","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2507.04094","title":"MMMOS: Multi-domain Multi-axis Audio Quality Assessment","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2606.14466","title":"The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2608.05145","title":"Objects as Audio-Visual Modal Sound Fields","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.30951","title":"Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}