{"total":21,"rows":[{"id":"2408.14080","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","created":"2024-08-26","cited_by_count":21,"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":"2505.06224","title":"Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks","created":"2025-05-09","cited_by_count":7,"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":"2502.12511","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2501.00064","title":"Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2602.21772","title":"UniWhisper: Efficient Continual Multi-task Training for Robust Universal Audio Representation","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2506.21174","title":"Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.20052","title":"Improving Deep Learning-based Respiratory Sound Analysis with Frequency Selection and Attention Mechanism","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2509.26291","title":"Representation-Based Data Quality Audits for Audio","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.03637","title":"AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.14961","title":"Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2512.22564","title":"Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.21612","title":"Representation-Regularized Convolutional Audio Transformer for Audio Understanding","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.13749","title":"Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.24096","title":"Meta-Ensemble Learning with Diverse Data Splits for Improved Respiratory Sound Classification","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.01909","title":"Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.11922","title":"Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.30700","title":"BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.25887","title":"Device Invariance using Domain Adaptation on Acoustic Scene Classification","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}