{"total":44,"rows":[{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"area":null},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2205.09248","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","created":"2022-05-18","cited_by_count":23,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2311.01052","title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2401.12238","title":"Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2109.10581","title":"DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2208.04654","title":"Extending GCC-PHAT using Shift Equivariant Neural Networks","created":"2022-08-09","cited_by_count":7,"area":null},{"id":"2308.09514","title":"Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning","created":"2023-08-18","cited_by_count":7,"area":null},{"id":"2308.00219","title":"Multi-goal Audio-visual Navigation using Sound Direction Map","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2406.04706","title":"Winner-takes-all learners are geometry-aware conditional density estimators","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2309.08295","title":"A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2203.16940","title":"Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2210.05917","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","created":"2022-10-12","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":"2308.04169","title":"Dual input neural networks for positional sound source localization","created":"2023-08-08","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":"2508.03724","title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2506.23437","title":"From Large-scale Audio Tagging to Real-Time Explainable Emergency Vehicle Sirens Detection","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2601.19821","title":"Query-Guided Spatial-Temporal-Frequency Interaction for Music Audio-Visual Question Answering","created":"2026-01-27","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":"2303.15223","title":"How far generated data can impact Neural Networks performance?","created":"2023-03-27","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":"2408.15771","title":"wav2pos: Sound Source Localization using Masked Autoencoders","created":"2024-08-28","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":"2607.02343","title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2205.02376","title":"Uncertainty-Based Non-Parametric Active Peak Detection","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2208.04938","title":"A physically-informed Deep-Learning approach for locating sources in a waveguide","created":"2022-08-07","cited_by_count":0,"area":null},{"id":"2306.15942","title":"Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2309.06661","title":"Sound field decomposition based on two-stage neural networks","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2310.06260","title":"An experiment on an automated literature survey of data-driven speech enhancement methods","created":"2023-10-10","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":"2404.01611","title":"Audio Simulation for Sound Source Localization in Virtual Evironment","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2406.17103","title":"Maximum Likelihood Estimation of the Direction of Sound In A Reverberant Noisy Environment","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2411.13179","title":"SONNET: Enhancing Time Delay Estimation by Leveraging Simulated Audio","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2505.20961","title":"Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2508.00307","title":"Acoustic Imaging for UAV Detection: Dense Beamformed Energy Maps and U-Net SELD","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2508.14115","title":"Towards Low-Latency Tracking of Multiple Speakers With Short-Context Speaker Embeddings","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.13487","title":"Systematic Evaluation of Time-Frequency Features for Binaural Sound Source Localization","created":"2025-11-17","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":"2609.32224","title":"RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}