{"total":45,"rows":[{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2106.09296","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","created":"2021-06-17","cited_by_count":91,"area":null},{"id":"2304.04640","title":"NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems","created":"2023-04-10","cited_by_count":27,"area":null},{"id":"2206.12513","title":"Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2210.02287","title":"TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene","created":"2022-10-05","cited_by_count":12,"area":null},{"id":"2203.15751","title":"A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2305.07499","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2206.13909","title":"QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2105.02702","title":"MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2203.12314","title":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","created":"2022-03-23","cited_by_count":7,"area":null},{"id":"2402.02694","title":"Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2111.06531","title":"Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2211.06073","title":"SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2107.01461","title":"A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification","created":"2021-07-03","cited_by_count":4,"area":null},{"id":"2110.01506","title":"Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations","created":"2021-10-04","cited_by_count":4,"area":null},{"id":"2309.16369","title":"Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2509.04166","title":"Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2207.11529","title":"Low-complexity CNNs for Acoustic Scene Classification","created":"2022-07-23","cited_by_count":3,"area":null},{"id":"2310.15648","title":"Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2411.00973","title":"Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2110.08598","title":"A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer","created":"2021-10-16","cited_by_count":2,"area":null},{"id":"2408.06264","title":"Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2104.07213","title":"Attentive max feature map and joint training for acoustic scene classification","created":"2021-04-15","cited_by_count":1,"area":null},{"id":"2110.09598","title":"Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2210.08610","title":"Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2212.11277","title":"Audio Denoising for Robust Audio Fingerprinting","created":"2022-12-21","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":"2412.11943","title":"autrainer: A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2107.08933","title":"Over-Parameterization and Generalization in Audio Classification","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2203.04114","title":"A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification","created":"2022-03-07","cited_by_count":0,"area":null},{"id":"2204.12177","title":"A Comparative Study on Approaches to Acoustic Scene Classification using CNNs","created":"2022-04-26","cited_by_count":0,"area":null},{"id":"2208.01555","title":"Low-complexity CNNs for Acoustic Scene Classification","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2310.13388","title":"Music Augmentation and Denoising For Peak-Based Audio Fingerprinting","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2405.03567","title":"Deep Space Separable Distillation for Lightweight Acoustic Scene Classification","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2503.16862","title":"Improving Acoustic Scene Classification with City Features","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2504.07345","title":"Quantum-Inspired Genetic Algorithm for Robust Source Separation in Smart City Acoustics","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2509.11168","title":"An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.17345","title":"DDSC: Dynamic Dual-Signal Curriculum for Data-Efficient Acoustic Scene Classification under Domain Shift","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.17281","title":"LibriVAD: A Scalable Open Dataset with Deep Learning Benchmarks for Voice Activity Detection","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.01394","title":"SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.25476","title":"How Class Ontology and Data Scale Affect Audio Transfer Learning","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.04383","title":"Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding","created":"2026-07-05","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":"2610.01926","title":"LAST: Looped Audio Spectrogram Transformer","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}