{"total":42,"rows":[{"id":"2111.09639","title":"Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction","created":"2021-11-18","cited_by_count":34,"area":null},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2109.00962","title":"You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2110.02011","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2408.08673","title":"MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2102.05843","title":"Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification","created":"2021-02-11","cited_by_count":5,"area":null},{"id":"2203.11997","title":"Federated Self-Supervised Learning for Acoustic Event Classification","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2505.04419","title":"Recognizing Ornaments in Vocal Indian Art Music with Active Annotation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2106.06858","title":"Improving weakly supervised sound event detection with self-supervised auxiliary tasks","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","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":"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":"2111.02041","title":"A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches","created":"2021-11-03","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":"2409.17656","title":"Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2102.09959","title":"Artificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast","created":"2021-02-19","cited_by_count":2,"area":null},{"id":"2105.13392","title":"Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2402.03383","title":"MCU-Net: A Multi-prior Collaborative Deep Unfolding Network with Gates-controlled Spatial Attention for Accelerated MR Image Reconstruction","created":"2024-02-04","cited_by_count":2,"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":"2603.19660","title":"Semantic Audio-Visual Navigation in Continuous Environments","created":"2026-03-20","cited_by_count":2,"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":"2508.07829","title":"Auditory Intelligence: Understanding the World Through Sound","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2106.07428","title":"Audio Attacks and Defenses against AED Systems -- A Practical Study","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2107.10471","title":"Improving Polyphonic Sound Event Detection on Multichannel Recordings with the S{\\o}rensen-Dice Coefficient Loss and Transfer Learning","created":"2021-07-22","cited_by_count":0,"area":null},{"id":"2111.01205","title":"Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset","created":"2021-11-01","cited_by_count":0,"area":null},{"id":"2203.15576","title":"Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition","created":"2022-03-28","cited_by_count":0,"area":null},{"id":"2306.16054","title":"Improving Primate Sounds Classification using Binary Presorting for Deep Learning","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2308.11530","title":"Leveraging Language Model Capabilities for Sound Event Detection","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2501.01908","title":"Training-Free Adversarial Robustness in Computational MRI","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2503.11373","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2504.04428","title":"Formula-Supervised Sound Event Detection: Pre-Training Without Real Data","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2507.01563","title":"Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.21642","title":"Whilter: A Whisper-based Data Filter for \"In-the-Wild\" Speech Corpora Using Utterance-level Multi-Task Classification","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2602.01850","title":"WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.03934","title":"Towards Open World Sound Event Detection","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.25404","title":"Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.22218","title":"An Analysis of Untrained Deep Reservoir Networks for Audio Surveillance","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.14287","title":"Acoustic UAV Detection in Battlefield Scenarios: Handling Noise, Domain Shift, and Weak Labels","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.15215","title":"Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.34907","title":"SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}