{"total":21,"rows":[{"id":"2208.07204","title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","created":"2022-08-12","cited_by_count":95,"area":null},{"id":"2206.03065","title":"Universal Speech Enhancement with Score-based Diffusion","created":"2022-06-07","cited_by_count":75,"area":null},{"id":"2408.16589","title":"CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions","created":"2024-08-29","cited_by_count":34,"area":null},{"id":"2201.02331","title":"iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection","created":"2022-01-07","cited_by_count":27,"area":null},{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2105.00349","title":"Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise","created":"2021-05-01","cited_by_count":10,"area":null},{"id":"2305.10709","title":"NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing","created":"2023-05-18","cited_by_count":8,"area":null},{"id":"2107.10716","title":"Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2110.00046","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2105.02132","title":"Self-Supervised Learning from Automatically Separated Sound Scenes","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2107.00623","title":"Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks","created":"2021-07-01","cited_by_count":5,"area":null},{"id":"2411.04036","title":"Stepping Forward on the Last Mile","created":"2024-11-06","cited_by_count":4,"area":null},{"id":"2104.09045","title":"Do We Really Need Gold Samples for Sample Weighting Under Label Noise?","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2109.09227","title":"ARCA23K: An audio dataset for investigating open-set label noise","created":"2021-09-19","cited_by_count":3,"area":null},{"id":"2303.05007","title":"Towards Robust Image-in-Audio Deep Steganography","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"area":null},{"id":"2206.11260","title":"Few-shot Long-Tailed Bird Audio Recognition","created":"2022-06-22","cited_by_count":1,"area":null},{"id":"2507.21642","title":"Whilter: A Whisper-based Data Filter for \"In-the-Wild\" Speech Corpora Using Utterance-level Multi-Task Classification","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.02349","title":"Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.26291","title":"Representation-Based Data Quality Audits for Audio","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2607.19033","title":"Content is What Remains: Invariant Speech Tokenization from Parallel Utterances","created":"2026-07-21","cited_by_count":0,"area":null}],"next_cursor":null}