{"total":13,"rows":[{"id":"2106.06426","title":"Catch-A-Waveform: Learning to Generate Audio from a Single Short Example","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","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":"2204.13289","title":"Music Enhancement via Image Translation and Vocoding","created":"2022-04-28","cited_by_count":11,"area":null},{"id":"2501.11311","title":"A2SB: Audio-to-Audio Schrodinger Bridges","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2402.09318","title":"Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2211.07951","title":"Show Me the Instruments: Musical Instrument Retrieval from Mixture Audio","created":"2022-11-15","cited_by_count":4,"area":null},{"id":"2211.08379","title":"Music Instrument Classification Reprogrammed","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2204.08269","title":"Differentiable Time-Frequency Scattering on GPU","created":"2022-04-18","cited_by_count":1,"area":null},{"id":"2211.13152","title":"Introducing topography in convolutional neural networks","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2307.12576","title":"Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2309.11895","title":"Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2506.17499","title":"Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Training","created":"2025-06-20","cited_by_count":0,"area":null}],"next_cursor":null}