{"total":15,"rows":[{"id":"2102.05749","title":"Self-Supervised VQ-VAE for One-Shot Music Style Transfer","created":"2021-02-10","cited_by_count":14,"area":null},{"id":"2211.05385","title":"GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning","created":"2022-11-10","cited_by_count":9,"area":null},{"id":"2108.01450","title":"Is Disentanglement enough? On Latent Representations for Controllable Music Generation","created":"2021-08-01","cited_by_count":7,"area":null},{"id":"2508.01464","title":"Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians","created":"2025-08-02","cited_by_count":6,"area":null},{"id":"2202.06180","title":"Learning long-term music representations via hierarchical contextual constraints","created":"2022-02-13","cited_by_count":5,"area":null},{"id":"2304.11648","title":"Towards Controllable Audio Texture Morphing","created":"2023-04-23","cited_by_count":4,"area":null},{"id":"2408.10807","title":"DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation","created":"2024-08-20","cited_by_count":3,"area":null},{"id":"2110.06434","title":"DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2111.05174","title":"CAESynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders","created":"2021-11-09","cited_by_count":1,"area":null},{"id":"2401.04558","title":"HyperGANStrument: Instrument Sound Synthesis and Editing with Pitch-Invariant Hypernetworks","created":"2024-01-09","cited_by_count":1,"area":null},{"id":"2407.10328","title":"The Interpretation Gap in Text-to-Music Generation Models","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2602.10058","title":"Evaluating Disentangled Representations for Controllable Music Generation","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2107.06231","title":"Timbre Classification of Musical Instruments with a Deep Learning Multi-Head Attention-Based Model","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2109.10640","title":"LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders","created":"2021-09-22","cited_by_count":0,"area":null},{"id":"2111.12588","title":"Towards Cross-Cultural Analysis using Music Information Dynamics","created":"2021-11-24","cited_by_count":0,"area":null}],"next_cursor":null}