{"total":48,"rows":[{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2111.01256","title":"Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2506.00343","title":"The iNaturalist Sounds Dataset","created":"2025-05-31","cited_by_count":17,"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":"2203.09129","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2402.17467","title":"Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2211.11479","title":"A Dataset for Greek Traditional and Folk Music: Lyra","created":"2022-11-21","cited_by_count":9,"area":null},{"id":"2103.02420","title":"Multi-view Audio and Music Classification","created":"2021-03-03","cited_by_count":8,"area":null},{"id":"2103.00768","title":"Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2109.10038","title":"VPN: Video Provenance Network for Robust Content Attribution","created":"2021-09-21","cited_by_count":7,"area":null},{"id":"2212.02055","title":"Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes","created":"2022-12-05","cited_by_count":7,"area":null},{"id":"2212.06735","title":"POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification","created":"2022-12-13","cited_by_count":7,"area":null},{"id":"2102.00201","title":"Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2102.05843","title":"Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification","created":"2021-02-11","cited_by_count":5,"area":null},{"id":"2207.04471","title":"Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation","created":"2022-07-10","cited_by_count":5,"area":null},{"id":"2310.10159","title":"Joint Music and Language Attention Models for Zero-shot Music Tagging","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2112.07627","title":"Visualizing Ensemble Predictions of Music Mood","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2207.13909","title":"Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2111.02041","title":"A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches","created":"2021-11-03","cited_by_count":3,"area":null},{"id":"2112.00702","title":"Semi-supervised music emotion recognition using noisy student training and harmonic pitch class profiles","created":"2021-12-01","cited_by_count":3,"area":null},{"id":"2210.05917","title":"Enemy Spotted: in-game gun sound dataset for gunshot classification and localization","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2302.08632","title":"jazznet: A Dataset of Fundamental Piano Patterns for Music Audio Machine Learning Research","created":"2023-02-17","cited_by_count":3,"area":null},{"id":"2308.04169","title":"Dual input neural networks for positional sound source localization","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2309.04762","title":"AudRandAug: Random Image Augmentations for Audio Classification","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2102.09959","title":"Artificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast","created":"2021-02-19","cited_by_count":2,"area":null},{"id":"2109.03309","title":"CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2202.02115","title":"Polyphonic pitch detection with convolutional recurrent neural networks","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2208.12086","title":"A Study on Broadcast Networks for Music Genre Classification","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2306.14191","title":"PrimaDNN': A Characteristics-aware DNN Customization for Singing Technique Detection","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2308.02421","title":"Differentiable short-time Fourier transform with respect to the hop length","created":"2023-07-26","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":"2408.13201","title":"EAViT: External Attention Vision Transformer for Audio Classification","created":"2024-08-23","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":"2209.04109","title":"MATT: A Multiple-instance Attention Mechanism for Long-tail Music Genre Classification","created":"2022-09-09","cited_by_count":0,"area":null},{"id":"2211.13285","title":"Proceedings of the 4th International Workshop on Reading Music Systems","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2306.16054","title":"Improving Primate Sounds Classification using Binary Presorting for Deep Learning","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2309.13373","title":"Asca: less audio data is more insightful","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2311.07164","title":"Pruning random resistive memory for optimizing analogue AI","created":"2023-11-13","cited_by_count":0,"area":null},{"id":"2311.12130","title":"Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2410.08321","title":"Music Genre Classification using Large Language Models","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2410.23325","title":"Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-soprano","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2504.10821","title":"Progressive Rock Music Classification","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2509.07756","title":"Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2512.13998","title":"Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.20744","title":"Voices of the Mountains: Deep Learning-Based Vocal Error Detection System for Kurdish Maqams","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.15440","title":"Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.26346","title":"Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Sounds","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}