{"total":85,"rows":[{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2102.01998","title":"Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond","created":"2021-02-03","cited_by_count":76,"area":null},{"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":"2310.20496","title":"BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis","created":"2023-10-31","cited_by_count":41,"area":null},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40,"area":null},{"id":"2103.15566","title":"Contrastive Domain Adaptation","created":"2021-03-26","cited_by_count":36,"area":null},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2206.03393","title":"Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition","created":"2022-06-07","cited_by_count":23,"area":null},{"id":"2209.11112","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","created":"2022-09-22","cited_by_count":23,"area":null},{"id":"2303.06365","title":"Explainable AI for Time Series via Virtual Inspection Layers","created":"2023-03-11","cited_by_count":23,"area":null},{"id":"2307.05527","title":"The Ethical Implications of Generative Audio Models: A Systematic Literature Review","created":"2023-07-07","cited_by_count":18,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2110.13290","title":"Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications","created":"2021-10-25","cited_by_count":17,"area":null},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2302.04959","title":"Hypernetworks build Implicit Neural Representations of Sounds","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2311.11420","title":"LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms","created":"2023-11-19","cited_by_count":11,"area":null},{"id":"2107.04386","title":"Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression","created":"2021-07-09","cited_by_count":10,"area":null},{"id":"2202.08679","title":"Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines","created":"2022-02-17","cited_by_count":10,"area":null},{"id":"2306.11229","title":"Reasoning over the Air: A Reasoning-based Implicit Semantic-Aware Communication Framework","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2104.10116","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2203.00554","title":"Neural Score Matching for High-Dimensional Causal Inference","created":"2022-03-01","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":"2103.03483","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2104.08954","title":"Combining a Convolutional Neural Network with Autoencoders to Predict the Survival Chance of COVID-19 Patients","created":"2021-04-18","cited_by_count":5,"area":null},{"id":"2203.11570","title":"Conditional Generative Data Augmentation for Clinical Audio Datasets","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2211.16028","title":"JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus","created":"2022-11-29","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2501.04967","title":"Targeted Adversarial Denoising Autoencoders (TADA) for Neural Time Series Filtration","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2103.06575","title":"An unsupervised deep learning framework for medical image denoising","created":"2021-03-11","cited_by_count":4,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2308.13816","title":"Homological Convolutional Neural Networks","created":"2023-08-26","cited_by_count":4,"area":null},{"id":"2107.09519","title":"Canonical Polyadic Decomposition and Deep Learning for Machine Fault Detection","created":"2021-07-20","cited_by_count":3,"area":null},{"id":"2303.06438","title":"On Neural Architectures for Deep Learning-based Source Separation of Co-Channel OFDM Signals","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2311.09655","title":"Multi-View Spectrogram Transformer for Respiratory Sound Classification","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2407.00465","title":"Characterizing Continual Learning Scenarios and Strategies for Audio Analysis","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2507.03273","title":"Event2Audio: Event-Based Optical Vibration Sensing","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2601.07331","title":"SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2111.10235","title":"Interpreting deep urban sound classification using Layer-wise Relevance Propagation","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2205.07682","title":"L3-Net Deep Audio Embeddings to Improve COVID-19 Detection from Smartphone Data","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2303.15114","title":"Automatic breach detection during spine pedicle drilling based on vibroacoustic sensing","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2305.16753","title":"ElectrodeNet -- A Deep Learning Based Sound Coding Strategy for Cochlear Implants","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2311.02369","title":"TACNET: Temporal Audio Source Counting Network","created":"2023-11-04","cited_by_count":2,"area":null},{"id":"2401.07575","title":"Cascaded Cross-Modal Transformer for Audio-Textual Classification","created":"2024-01-15","cited_by_count":2,"area":null},{"id":"2407.01607","title":"Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2409.08763","title":"Energy Consumption Trends in Sound Event Detection Systems","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2105.00202","title":"One-shot learning for acoustic identification of bird species in non-stationary environments","created":"2021-05-01","cited_by_count":1,"area":null},{"id":"2207.13434","title":"End-To-End Audiovisual Feature Fusion for Active Speaker Detection","created":"2022-07-27","cited_by_count":1,"area":null},{"id":"2211.02874","title":"Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data","created":"2022-11-05","cited_by_count":1,"area":null},{"id":"2211.03144","title":"MiddleGAN: Generate Domain Agnostic Samples for Unsupervised Domain Adaptation","created":"2022-11-06","cited_by_count":1,"area":null},{"id":"2301.01223","title":"ExploreADV: Towards exploratory attack for Neural Networks","created":"2023-01-01","cited_by_count":1,"area":null},{"id":"2305.03391","title":"Compressing audio CNNs with graph centrality based filter pruning","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2311.00801","title":"GIST: Generated Inputs Sets Transferability in Deep Learning","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2403.01046","title":"A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2408.02033","title":"Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2410.15620","title":"Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2410.18972","title":"Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2105.11836","title":"A Modulation Front-End for Music Audio Tagging","created":"2021-05-25","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":"2202.11283","title":"Better Modelling Out-of-Distribution Regression on Distributed Acoustic Sensor Data Using Anchored Hidden State Mixup","created":"2022-02-23","cited_by_count":0,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.06064","title":"Climate Change & Computer Audition: A Call to Action and Overview on Audio Intelligence to Help Save the Planet","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2203.17012","title":"A Temporal-oriented Broadcast ResNet for COVID-19 Detection","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2206.07176","title":"Frequency-centroid features for word recognition of non-native English speakers","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2208.03084","title":"Deep Feature Learning for Medical Acoustics","created":"2022-08-05","cited_by_count":0,"area":null},{"id":"2212.03243","title":"Machine Learning Assisted Inverse Design of Microresonators","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2306.06036","title":"SNeL: A Structured Neuro-Symbolic Language for Entity-Based Multimodal Scene Understanding","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2308.02263","title":"Efficient Monaural Speech Enhancement using Spectrum Attention Fusion","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2309.01574","title":"Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data","created":"2023-09-04","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":"2406.18757","title":"The Impact of Feature Representation on the Accuracy of Photonic Neural Networks","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2407.00696","title":"Graph in Graph Neural Network","created":"2024-06-30","cited_by_count":0,"area":null},{"id":"2407.15423","title":"Integrating IP Broadcasting with Audio Tags: Workflow and Challenges","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2409.13881","title":"Investigation of Time-Frequency Feature Combinations with Histogram Layer Time Delay Neural Networks","created":"2024-09-20","cited_by_count":0,"area":null},{"id":"2412.10011","title":"Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2412.14744","title":"Finite Sample Bounds for Non-Parametric Regression: Optimal Sample Efficiency and Space Complexity","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2504.00174","title":"MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2507.20052","title":"Improving Deep Learning-based Respiratory Sound Analysis with Frequency Selection and Attention Mechanism","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2508.03764","title":"CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2511.15675","title":"MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2512.04287","title":"Artificial Intelligence Applications in Horizon Scanning for Infectious Diseases","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2603.10623","title":"Geo-ATBench: A Benchmark for Geospatial Audio Tagging with Geospatial Semantic Context","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2606.02341","title":"Parameter-efficient Dual-encoder Architecture with Differentiable Choquet Integral Fusion for Underwater Acoustic Classification","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}