{"total":28,"rows":[{"id":"2401.06091","title":"A Closer Look at AUROC and AUPRC under Class Imbalance","created":"2024-01-11","cited_by_count":57,"area":null},{"id":"2202.11479","title":"Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF","created":"2022-02-23","cited_by_count":23,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2107.04954","title":"ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data","created":"2021-07-11","cited_by_count":20,"area":null},{"id":"2110.09127","title":"SpecTNT: a Time-Frequency Transformer for Music Audio","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2403.13086","title":"Listenable Maps for Audio Classifiers","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2404.10420","title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","created":"2024-04-16","cited_by_count":10,"area":null},{"id":"2106.07787","title":"Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities","created":"2021-06-14","cited_by_count":9,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2312.11234","title":"Perceptual Musical Features for Interpretable Audio Tagging","created":"2023-12-18","cited_by_count":7,"area":null},{"id":"2206.10805","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2208.11671","title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2305.07132","title":"Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2305.19602","title":"Learning Music Sequence Representation from Text Supervision","created":"2023-05-31","cited_by_count":5,"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":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2110.08862","title":"Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2302.00286","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2409.10496","title":"MusicLIME: Explainable Multimodal Music Understanding","created":"2024-09-16","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":"2212.10901","title":"ALCAP: Alignment-Augmented Music Captioner","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2311.18749","title":"TransCORALNet: A Two-Stream Transformer CORAL Networks for Supply Chain Credit Assessment Cold Start","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2401.15323","title":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","created":"2024-01-27","cited_by_count":1,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2104.02309","title":"MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2505.17233","title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2508.03780","title":"Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition","created":"2025-08-05","cited_by_count":0,"area":null}],"next_cursor":null}