{"total":74,"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":"2110.04176","title":"PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2202.06406","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","created":"2022-02-13","cited_by_count":19,"area":null},{"id":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","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":"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":"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":"2211.14419","title":"Panoramic Video Salient Object Detection with Ambisonic Audio Guidance","created":"2022-11-26","cited_by_count":9,"area":null},{"id":"2106.06969","title":"SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform","created":"2021-06-13","cited_by_count":8,"area":null},{"id":"2201.12771","title":"Self-Supervised Moving Vehicle Detection from Audio-Visual Cues","created":"2022-01-30","cited_by_count":8,"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":"2106.03903","title":"PILOT: Introducing Transformers for Probabilistic Sound Event Localization","created":"2021-06-07","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":"2103.00417","title":"Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization","created":"2021-02-28","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":"2101.10636","title":"Semi-supervised source localization in reverberant environments with deep generative modeling","created":"2021-01-26","cited_by_count":5,"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":"2112.11547","title":"Decompose the Sounds and Pixels, Recompose the Events","created":"2021-12-21","cited_by_count":4,"area":null},{"id":"2503.02389","title":"Robust detection of overlapping bioacoustic sound events","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2504.08907","title":"Spatial Audio Processing with Large Language Model on Wearable Devices","created":"2025-04-11","cited_by_count":4,"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":"2203.16940","title":"Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2210.14536","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":"2307.08663","title":"Quaternion Convolutional Neural Networks: Current Advances and Future Directions","created":"2023-07-17","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":"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":"2107.12033","title":"Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio","created":"2021-07-26","cited_by_count":2,"area":null},{"id":"2112.04914","title":"End-to-end Alexa Device Arbitration","created":"2021-12-08","cited_by_count":2,"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":"2601.12345","title":"Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios","created":"2026-01-18","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":"2102.11588","title":"Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain","created":"2021-02-23","cited_by_count":1,"area":null},{"id":"2103.01830","title":"Audio scene monitoring using redundant ad-hoc microphone array networks","created":"2021-03-02","cited_by_count":1,"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":"2209.05900","title":"Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification","created":"2022-09-13","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":"2306.14191","title":"PrimaDNN': A Characteristics-aware DNN Customization for Singing Technique Detection","created":"2023-06-25","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":"2406.13579","title":"Automated Bioacoustic Monitoring for South African Bird Species on Unlabeled Data","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2412.08356","title":"Zero-Shot Mono-to-Binaural Speech Synthesis","created":"2024-12-11","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":"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":"2603.23723","title":"Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers","created":"2026-03-24","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":"2204.09919","title":"Sonic Interactions in Virtual Environments: the Egocentric Audio Perspective of the Digital Twin","created":"2022-04-21","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":"2307.08466","title":"Generalizable Classification of UHF Partial Discharge Signals in Gas-Insulated HVDC Systems Using Neural Networks","created":"2023-07-17","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":"2310.19063","title":"Feature Aggregation in Joint Sound Classification and Localization Neural Networks","created":"2023-10-29","cited_by_count":0,"area":null},{"id":"2312.10756","title":"Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios","created":"2023-12-17","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":"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},{"id":"2510.05828","title":"StereoSync: Spatially-Aware Stereo Audio Generation from Video","created":"2025-10-07","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":"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":"2601.18335","title":"Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2607.15265","title":"SceneBind: Binding What and Where Across Vision, Audio and Language","created":"2026-07-16","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":"2609.34347","title":"SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former","created":"2026-09-28","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}],"next_cursor":null}