{"total":52,"rows":[{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"id":"2105.00899","title":"Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series","created":"2021-05-03","cited_by_count":29,"area":null},{"id":"2208.00368","title":"Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction","created":"2022-07-31","cited_by_count":29,"area":null},{"id":"2201.05562","title":"Investigation of Data Augmentation Techniques for Disordered Speech Recognition","created":"2022-01-14","cited_by_count":27,"area":null},{"id":"2107.09539","title":"Parametric Scattering Networks","created":"2021-07-20","cited_by_count":16,"area":null},{"id":"2109.02774","title":"FastAudio: A Learnable Audio Front-End for Spoof Speech Detection","created":"2021-09-06","cited_by_count":8,"area":null},{"id":"2111.02585","title":"InQSS: a speech intelligibility and quality assessment model using a multi-task learning network","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2102.10322","title":"Learnable MFCCs for Speaker Verification","created":"2021-02-20","cited_by_count":6,"area":null},{"id":"2205.14627","title":"Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces","created":"2022-05-29","cited_by_count":6,"area":null},{"id":"2207.10939","title":"Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis","created":"2022-07-22","cited_by_count":6,"area":null},{"id":"2209.15261","title":"Minimalistic Unsupervised Learning with the Sparse Manifold Transform","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2206.09222","title":"Bioinspired random projections for robust, sparse classification","created":"2022-06-18","cited_by_count":4,"area":null},{"id":"2204.03703","title":"Physics-assisted Generative Adversarial Network for X-Ray Tomography","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2402.17775","title":"WhaleNet: a Novel Deep Learning Architecture for Marine Mammals Vocalizations on Watkins Marine Mammal Sound Database","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2410.01482","title":"One Wave To Explain Them All: A Unifying Perspective On Feature Attribution","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2602.02980","title":"WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2105.04806","title":"Deep scattering network for speech emotion recognition","created":"2021-05-11","cited_by_count":2,"area":null},{"id":"2305.01294","title":"Differential Newborn Face Morphing Attack Detection using Wavelet Scatter Network","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2404.19649","title":"Landmark Alternating Diffusion","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2506.09674","title":"Wavelet Scattering Transform and Fourier Representation for Offline Detection of Malicious Clients in Federated Learning","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2606.30822","title":"Separation Capacity of Scattering Networks","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2106.00110","title":"A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling","created":"2021-05-31","cited_by_count":1,"area":null},{"id":"2109.08910","title":"MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification","created":"2021-09-18","cited_by_count":1,"area":null},{"id":"2111.08011","title":"Advantage of Machine Learning over Maximum Likelihood in Limited-Angle Low-Photon X-Ray Tomography","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2203.15519","title":"Learning neural audio features without supervision","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2211.15441","title":"Graceful Forgetting II. Data as a Process","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2311.06170","title":"Time Scale Network: A Shallow Neural Network For Time Series Data","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2402.15430","title":"Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2506.12039","title":"The Maximal Overlap Discrete Wavelet Scattering Transform and Its Application in Classification Tasks","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2507.21189","title":"Operator-Based Machine Intelligence: A Hilbert Space Framework for Spectral Learning and Symbolic Reasoning","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2509.21802","title":"ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2509.23103","title":"HTMA-Net: Towards Multiplication-Avoiding Neural Networks via Hadamard Transform and In-Memory Computing","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2605.17582","title":"Scale-Equivariant Generative Forecasting: Weight-Tied Dilated Convolutions, Wavelet Scattering Inputs, and Spectral-Consistency Training for Self-Similar Time Series","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2102.00841","title":"Dynamic Texture Recognition via Nuclear Distances on Kernelized Scattering Histogram Spaces","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2109.02773","title":"Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary Model","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2202.05169","title":"Radar-based Materials Classification Using Deep Wavelet Scattering Transform: A Comparison of Centimeter vs. Millimeter Wave Units","created":"2022-02-08","cited_by_count":0,"area":null},{"id":"2206.13365","title":"Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2210.09837","title":"Deep Scattering Spectrum germaneness to Fault Detection and Diagnosis for Component-level Prognostics and Health Management (PHM)","created":"2022-10-18","cited_by_count":0,"area":null},{"id":"2310.00602","title":"Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification","created":"2023-10-01","cited_by_count":0,"area":null},{"id":"2405.17697","title":"P4: Towards private, personalized, and Peer-to-Peer learning","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2502.00310","title":"SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2502.05722","title":"Explainable and Class-Revealing Signal Feature Extraction via Scattering Transform and Constrained Zeroth-Order Optimization","created":"2025-02-08","cited_by_count":0,"area":null},{"id":"2502.11105","title":"Graceful forgetting: Memory as a process","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2505.20950","title":"Scattering Networks on Noncommutative Finite Groups","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.02260","title":"MoCA: Multi-modal Cross-masked Autoencoder for Time Series in Digital Health","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2601.20401","title":"ScatterFusion: A Hierarchical Scattering Transform Framework for Enhanced Time Series Forecasting","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.11145","title":"SCRAPL: Scattering Transform with Random Paths for Machine Learning","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2606.27605","title":"On the stability of scale-space metrics","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05290","title":"ChatImage: Navigating Long-Form LLM Answers through Interactive Images","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.29372","title":"WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}