{"total":31,"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":"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":"2104.05499","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","created":"2021-04-12","cited_by_count":9,"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":"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":"2401.17129","title":"Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes","created":"2024-01-29","cited_by_count":3,"area":null},{"id":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"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":"2403.20130","title":"Sound event localization and classification using WASN in Outdoor Environment","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2408.17166","title":"Learning Multi-Target TDOA Features for Sound Event Localization and Detection","created":"2024-08-30","cited_by_count":1,"area":null},{"id":"2411.03172","title":"Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2411.14207","title":"HARP: A Large-Scale Higher-Order Ambisonic Room Impulse Response Dataset","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2507.01143","title":"A Review on Sound Source Localization in Robotics: Focusing on Deep Learning Methods","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.07066","title":"Latent Acoustic Mapping for Direction of Arrival Estimation: A Self-Supervised Approach","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2508.07829","title":"Auditory Intelligence: Understanding the World Through Sound","created":"2025-08-11","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":"2608.29999","title":"TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models","created":"2026-08-30","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":"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":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2606.22020","title":"What Do Neural Networks Learn for TDOA Estimation? A Cross-Architecture Probing Study","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2609.20223","title":"Before the Warning Comes Too Late: Incremental Phone-Scam Detection from Speech","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.23156","title":"EquiSELD: Efficient training of equivariant sound event localization and detection networks","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2610.05610","title":"SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}