{"total":85,"rows":[{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56,"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":"2105.14462","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","created":"2021-05-30","cited_by_count":44,"area":null},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2310.01211","title":"From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication","created":"2023-10-02","cited_by_count":21,"area":null},{"id":"2103.13549","title":"An evidential classifier based on Dempster-Shafer theory and deep learning","created":"2021-03-25","cited_by_count":18,"area":null},{"id":"2104.06517","title":"Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition","created":"2021-04-13","cited_by_count":15,"area":null},{"id":"2402.01424","title":"A Data-Driven Analysis of Robust Automatic Piano Transcription","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2411.14452","title":"Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2107.07029","title":"Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition","created":"2021-07-14","cited_by_count":14,"area":null},{"id":"2203.06760","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","created":"2022-03-13","cited_by_count":12,"area":"distill"},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2103.13620","title":"SubSpectral Normalization for Neural Audio Data Processing","created":"2021-03-25","cited_by_count":11,"area":null},{"id":"2211.13638","title":"Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes","created":"2022-11-24","cited_by_count":10,"area":null},{"id":"2308.06053","title":"Cost-effective On-device Continual Learning over Memory Hierarchy with Miro","created":"2023-08-11","cited_by_count":10,"area":null},{"id":"2304.00022","title":"What Makes for Effective Few-shot Point Cloud Classification?","created":"2023-03-31","cited_by_count":7,"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":"2103.01929","title":"SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification","created":"2021-03-02","cited_by_count":4,"area":null},{"id":"2103.12157","title":"Tiny Transformers for Environmental Sound Classification at the Edge","created":"2021-03-22","cited_by_count":4,"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":"2207.07429","title":"Continual Learning For On-Device Environmental Sound Classification","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2302.05110","title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization","created":"2023-02-10","cited_by_count":4,"area":null},{"id":"2303.15161","title":"Data Augmentation for Environmental Sound Classification Using Diffusion Probabilistic Model with Top-k Selection Discriminator","created":"2023-03-27","cited_by_count":4,"area":"diffusion"},{"id":"2102.05151","title":"Enhancing Audio Augmentation Methods with Consistency Learning","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2102.08833","title":"DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection","created":"2021-02-17","cited_by_count":3,"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":"2211.02940","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2309.04762","title":"AudRandAug: Random Image Augmentations for Audio Classification","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2102.08183","title":"Comparison of semi-supervised deep learning algorithms for audio classification","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2102.11771","title":"Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2104.02055","title":"Data augmentation for dealing with low sampling rates in NILM","created":"2021-03-30","cited_by_count":2,"area":null},{"id":"2107.11453","title":"Automatic Detection Of Noise Events at Shooting Range Using Machine Learning","created":"2021-07-23","cited_by_count":2,"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":"2208.11868","title":"Interpretable Multimodal Emotion Recognition using Hybrid Fusion of Speech and Image Data","created":"2022-08-25","cited_by_count":2,"area":null},{"id":"2301.08606","title":"Data Augmentation for Modeling Human Personality: The Dexter Machine","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2308.02287","title":"Frustratingly Easy Model Generalization by Dummy Risk Minimization","created":"2023-08-04","cited_by_count":2,"area":null},{"id":"2409.11059","title":"OneEncoder: A Lightweight Framework for Progressive Alignment of Modalities","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2410.06927","title":"Spectral and Rhythm Features for Audio Classification with Deep Convolutional Neural Networks","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2509.06027","title":"DreamAudio: Customized Text-to-Audio Generation with Diffusion Models","created":"2025-09-07","cited_by_count":2,"area":"diffusion"},{"id":"2605.13672","title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2106.12992","title":"SofaMyRoom: a fast and multiplatform \"shoebox\" room simulator for binaural room impulse response dataset generation","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2107.13237","title":"A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification","created":"2021-07-28","cited_by_count":1,"area":null},{"id":"2109.06171","title":"In-filter Computing For Designing Ultra-light Acoustic Pattern Recognizers","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2111.10897","title":"Health Monitoring of Industrial machines using Scene-Aware Threshold Selection","created":"2021-11-21","cited_by_count":1,"area":null},{"id":"2112.07285","title":"Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2204.07018","title":"From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks","created":"2022-04-14","cited_by_count":1,"area":null},{"id":"2309.12134","title":"Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2401.12729","title":"Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2403.17181","title":"On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2509.08717","title":"Explainability of CNN Based Classification Models for Acoustic Signal","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2604.14532","title":"CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2606.14791","title":"From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2101.01863","title":"Environment Transfer for Distributed Systems","created":"2021-01-06","cited_by_count":0,"area":null},{"id":"2103.07125","title":"Learning spectro-temporal representations of complex sounds with parameterized neural networks","created":"2021-03-12","cited_by_count":0,"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":"2108.04449","title":"An empirical investigation into audio pipeline approaches for classifying bird species","created":"2021-08-10","cited_by_count":0,"area":null},{"id":"2108.10254","title":"Automatic Speech Recognition And Limited Vocabulary: A Survey","created":"2021-08-23","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":"2111.07979","title":"Metric-based multimodal meta-learning for human movement identification via footstep recognition","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2203.06059","title":"Deep Convolutional Neural Network for Roadway Incident Surveillance Using Audio Data","created":"2022-03-09","cited_by_count":0,"area":null},{"id":"2205.09667","title":"The AI Mechanic: Acoustic Vehicle Characterization Neural Networks","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2207.08825","title":"Contrastive Environmental Sound Representation Learning","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2211.04734","title":"Framework Construction of an Adversarial Federated Transfer Learning Classifier","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2304.13963","title":"Human-machine knowledge hybrid augmentation method for surface defect detection based few-data learning","created":"2023-04-27","cited_by_count":0,"area":null},{"id":"2306.09906","title":"Correlation Clustering of Bird Sounds","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2309.13752","title":"Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2311.02278","title":"Machine learning's own Industrial Revolution","created":"2023-11-04","cited_by_count":0,"area":null},{"id":"2403.08438","title":"Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2407.10596","title":"An evaluation of CNN models and data augmentation techniques in hierarchical localization of mobile robots","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2501.01921","title":"Structural and Statistical Audio Texture Knowledge Distillation for Acoustic Classification","created":"2025-01-03","cited_by_count":0,"area":"distill"},{"id":"2502.15285","title":"Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANs","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2505.06042","title":"Learning Music Audio Representations With Limited Data","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2507.00755","title":"LearnAFE: Circuit-Algorithm Co-design Framework for Learnable Audio Analog Front-End","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2509.00839","title":"Adaptive Vehicle Speed Classification via BMCNN with Reinforcement Learning-Enhanced Acoustic Processing","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.10391","title":"Improving Audio Event Recognition with Consistency Regularization","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2509.24215","title":"Metamorphic Testing for Audio Content Moderation Software","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2512.06396","title":"AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in Cybersecurity","created":"2025-12-06","cited_by_count":0,"area":"agents"},{"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":"2606.19568","title":"Exploring Feature Extraction Technique Parameters for Acoustic Gunshot Classification","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.27762","title":"\"What's That Sound?\": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition","created":"2026-08-16","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}