{"total":25,"rows":[{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"area":null},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2108.04543","title":"Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future","created":"2021-08-10","cited_by_count":18,"area":null},{"id":"2411.00121","title":"I Can Hear You: Selective Robust Training for Deepfake Audio Detection","created":"2024-10-31","cited_by_count":13,"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":"2207.05508","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","created":"2022-07-12","cited_by_count":8,"area":null},{"id":"2102.10322","title":"Learnable MFCCs for Speaker Verification","created":"2021-02-20","cited_by_count":6,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2307.13821","title":"Fitting Auditory Filterbanks with Multiresolution Neural Networks","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2106.04275","title":"Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2309.05855","title":"Instabilities in Convnets for Raw Audio","created":"2023-09-11","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":"2506.09804","title":"Regularizing Learnable Feature Extraction for Automatic Speech Recognition","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2202.05236","title":"Learnable Nonlinear Compression for Robust Speaker Verification","created":"2022-02-10","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":"2105.11836","title":"A Modulation Front-End for Music Audio Tagging","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2108.10382","title":"Learning Sparse Analytic Filters for Piano Transcription","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2208.11700","title":"Low-Level Physiological Implications of End-to-End Learning of Speech Recognition","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2407.10828","title":"Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Method","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2409.15357","title":"A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2412.00312","title":"Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2505.07709","title":"ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration","created":"2025-05-12","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":"2509.04345","title":"AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.10031","title":"Unified Learnable 2D Convolutional Feature Extraction for ASR","created":"2025-09-12","cited_by_count":0,"area":null}],"next_cursor":null}