{"total":21,"rows":[{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2109.00663","title":"Controllable deep melody generation via hierarchical music structure representation","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2402.09508","title":"Arrange, Inpaint, and Refine: Steerable Long-term Music Audio Generation and Editing via Content-based Controls","created":"2024-02-14","cited_by_count":17,"area":null},{"id":"2108.05064","title":"Variable-Length Music Score Infilling via XLNet and Musically Specialized Positional Encoding","created":"2021-08-11","cited_by_count":14,"area":null},{"id":"2203.16165","title":"Symbolic music generation conditioned on continuous-valued emotions","created":"2022-03-30","cited_by_count":13,"area":null},{"id":"2301.12525","title":"Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling","created":"2023-01-29","cited_by_count":9,"area":null},{"id":"2112.15110","title":"Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning","created":"2021-12-30","cited_by_count":6,"area":null},{"id":"2307.01229","title":"EmoGen: Eliminating Subjective Bias in Emotional Music Generation","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2407.14700","title":"Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Control","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2407.20955","title":"Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2307.13005","title":"IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2202.00951","title":"TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2306.02613","title":"Controllable Lyrics-to-Melody Generation","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2311.15480","title":"Automatic Time Signature Determination for New Scores Using Lyrics for Latent Rhythmic Structure","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2312.10307","title":"MusER: Musical Element-Based Regularization for Generating Symbolic Music with Emotion","created":"2023-12-16","cited_by_count":2,"area":null},{"id":"2506.17497","title":"From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2305.11605","title":"MIDI-Draw: Sketching to Control Melody Generation","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2607.14537","title":"MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}