{"total":32,"rows":[{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17,"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":"2406.08920","title":"AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis","created":"2024-06-13","cited_by_count":14,"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":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2510.15148","title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","created":"2025-10-16","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":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","cited_by_count":5,"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":"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":"2410.22271","title":"Leveraging Reverberation and Visual Depth Cues for Sound Event Localization and Detection with Distance Estimation","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2506.00273","title":"SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2512.08282","title":"PAVAS: Physics-Aware Video-to-Audio Synthesis","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2601.11039","title":"SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models","created":"2026-01-16","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":"2606.14141","title":"Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources","created":"2026-06-12","cited_by_count":2,"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":"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":"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":"2507.04845","title":"Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos","created":"2025-07-07","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":"2509.06598","title":"Integrating Spatial and Semantic Embeddings for Stereo Sound Event Localization in Videos","created":"2025-09-08","cited_by_count":1,"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},{"id":"2601.17611","title":"ToS: A Team of Specialists ensemble framework for Stereo Sound Event Localization and Detection with distance estimation in Video","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2607.01295","title":"CNN Models for Microphone Array Covariance Matrix Upsampling and Acoustic Imaging","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.14558","title":"The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.23152","title":"Bearings: Self-Supervised Soundfield Embeddings from First-Order Ambisonics","created":"2026-09-19","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":"2610.01388","title":"Supervising Sound Localization by In-the-wild Egomotion","created":"2026-10-01","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}