{"total":24,"rows":[{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2306.09126","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","created":"2023-06-15","cited_by_count":41,"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":"2110.00745","title":"End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression","created":"2021-10-02","cited_by_count":6,"area":null},{"id":"2601.02954","title":"The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"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":"2106.15190","title":"DCASE 2021 Task 3: Spectrotemporally-aligned Features for Polyphonic Sound Event Localization and Detection","created":"2021-06-29","cited_by_count":3,"area":null},{"id":"2210.14536","title":"Position tracking of a varying number of sound sources with sliding permutation invariant training","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2603.19660","title":"Semantic Audio-Visual Navigation in Continuous Environments","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2203.04197","title":"Locate This, Not That: Class-Conditioned Sound Event DOA Estimation","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2302.09409","title":"LOCUS: LOcalization with Channel Uncertainty and Sporadic Energy","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2306.08510","title":"Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2312.14021","title":"Leveraging Visual Supervision for Array-based Active Speaker Detection and Localization","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2406.08771","title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2504.10793","title":"SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2607.02343","title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2107.10469","title":"What Makes Sound Event Localization and Detection Difficult? Insights from Error Analysis","created":"2021-07-22","cited_by_count":0,"area":null},{"id":"2107.14561","title":"TASK3 DCASE2021 Challenge: Sound event localization and detection using squeeze-excitation residual CNNs","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2110.06126","title":"Spatial mixup: Directional loudness modification as data augmentation for sound event localization and detection","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2210.13932","title":"CoLoC: Conditioned Localizer and Classifier for Sound Event Localization and Detection","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2310.19063","title":"Feature Aggregation in Joint Sound Classification and Localization Neural Networks","created":"2023-10-29","cited_by_count":0,"area":null},{"id":"2410.22803","title":"DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2501.10755","title":"An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null}],"next_cursor":null}