{"total":116,"rows":[{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83,"area":null},{"id":"2406.06185","title":"EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2307.15913","title":"Moisesdb: A dataset for source separation beyond 4-stems","created":"2023-07-29","cited_by_count":39,"area":null},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2502.13128","title":"SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation","created":"2025-02-18","cited_by_count":29,"area":null},{"id":"2309.07525","title":"SingFake: Singing Voice Deepfake Detection","created":"2023-09-14","cited_by_count":21,"area":null},{"id":"2408.14080","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","created":"2024-08-26","cited_by_count":21,"area":null},{"id":"2310.19180","title":"JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation","created":"2023-10-29","cited_by_count":17,"area":null},{"id":"2402.09871","title":"MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music","created":"2024-02-15","cited_by_count":16,"area":null},{"id":"2310.12404","title":"Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative Editing","created":"2023-10-19","cited_by_count":15,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","cited_by_count":15,"area":null},{"id":"2503.19611","title":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","created":"2025-03-25","cited_by_count":14,"area":null},{"id":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2407.15060","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","created":"2024-07-21","cited_by_count":11,"area":null},{"id":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2309.02539","title":"A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation","created":"2023-09-05","cited_by_count":8,"area":null},{"id":"2410.21269","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2512.12196","title":"AutoMV: An Automatic Multi-Agent System for Music Video Generation","created":"2025-12-13","cited_by_count":8,"area":null},{"id":"2406.18747","title":"A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2305.07489","title":"Benchmarks and leaderboards for sound demixing tasks","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2310.00140","title":"GASS: Generalizing Audio Source Separation with Large-scale Data","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2310.15130","title":"Novel-View Acoustic Synthesis from 3D Reconstructed Rooms","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2412.09428","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","created":"2024-12-12","cited_by_count":6,"area":null},{"id":"2504.09839","title":"SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis","created":"2025-04-14","cited_by_count":6,"area":null},{"id":"2506.01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2601.03888","title":"IndexTTS 2.5 Technical Report","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2408.06370","title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2505.21827","title":"Music Source Restoration","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.17404","title":"SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2603.24793","title":"AVControl: Efficient Framework for Training Audio-Visual Controls","created":"2026-03-25","cited_by_count":5,"area":null},{"id":"2306.09382","title":"Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2409.10995","title":"SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2603.16281","title":"Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2402.17701","title":"Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2407.08647","title":"From Real to Cloned Singer Identification","created":"2024-07-11","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":"2506.01322","title":"Zero-Shot Text-to-Speech for Vietnamese","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2603.09201","title":"The Radio-Frequency Transformer for Signal Separation","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2304.14226","title":"TorchBench: Benchmarking PyTorch with High API Surface Coverage","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2311.13987","title":"Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2407.03188","title":"MuDiT & MuSiT: Alignment with Colloquial Expression in Description-to-Song Generation","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2407.15828","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2410.03375","title":"SoundSignature: What Type of Music Do You Like?","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2502.10822","title":"NeuroAMP: A Novel End-to-end General Purpose Deep Neural Amplifier for Personalized Hearing Aids","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2503.07352","title":"Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical Music","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2506.14684","title":"Refining music sample identification with a self-supervised graph neural network","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.01339","title":"User-guided Generative Source Separation","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2601.02357","title":"DARC: Drum accompaniment generation with fine-grained rhythm control","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.21260","title":"Music Plagiarism Detection: Problem Formulation and a Segment-based Solution","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.02630","title":"Trailer Reimagined: An Innovative, Llm-DRiven, Expressive Automated Movie Summary framework (TRAILDREAMS)","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2605.29300","title":"MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2306.12714","title":"Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies","created":"2023-06-22","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":"2406.16932","title":"Xi-Net: Transformer Based Seismic Waveform Reconstructor","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2408.12658","title":"Hierarchical Generative Modeling of Melodic Vocal Contours in Hindustani Classical Music","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2409.05095","title":"The first Cadenza challenges: using machine learning competitions to improve music for listeners with a hearing loss","created":"2024-09-08","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":"2409.18705","title":"Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2502.04722","title":"Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2504.07229","title":"Visual-Aware Speech Recognition for Noisy Scenarios","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2507.04554","title":"Self-supervised learning of speech representations with Dutch archival data","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2509.08282","title":"Real-world Music Plagiarism Detection With Music Segment Transcription System","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2509.23364","title":"AI-Assisted Music Production: A User Study on Text-to-Music Models","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.11507","title":"Automatic Music Sample Identification with Multi-Track Contrastive Learning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.21247","title":"The Spheres Dataset: Multitrack Orchestral Recordings for Music Source Separation and Information Retrieval","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2605.12135","title":"STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.29488","title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2609.08275","title":"Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2303.02599","title":"Hybrid Y-Net Architecture for Singing Voice Separation","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2304.02160","title":"Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2305.01051","title":"LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Music","created":"2023-05-01","cited_by_count":0,"area":null},{"id":"2305.01758","title":"Adversarial Generative NMF for Single Channel Source Separation","created":"2023-04-24","cited_by_count":0,"area":null},{"id":"2305.12200","title":"ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2401.12068","title":"Resource-constrained stereo singing voice cancellation","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2406.16315","title":"Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2407.00657","title":"Improving Real-Time Music Accompaniment Separation with MMDenseNet","created":"2024-06-30","cited_by_count":0,"area":null},{"id":"2409.01885","title":"Activity-Guided Industrial Anomalous Sound Detection against Interferences","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2409.09866","title":"S2Cap: A Benchmark and a Baseline for Singing Style Captioning","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2411.01661","title":"Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2411.04337","title":"Neural-Enhanced Dynamic Range Compression Inversion: A Hybrid Approach for Restoring Audio Dynamics","created":"2024-11-07","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":"2505.17823","title":"Source Separation of Small Classical Ensembles: Challenges and Opportunities","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.23509","title":"Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2506.14571","title":"The Perception of Phase Intercept Distortion and its Application in Data Augmentation","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2508.14556","title":"Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.13285","title":"Contrastive timbre representations for musical instrument and synthesizer retrieval","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.26580","title":"Source Separation for A Cappella Music","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.05756","title":"Transcribing Rhythmic Patterns of the Guitar Track in Polyphonic Music","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.22295","title":"VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2511.17136","title":"Device-Guided Music Transfer","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.15532","title":"A Conditioned UNet for Music Source Separation","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.14786","title":"Training-Efficient Text-to-Music Generation with State-Space Modeling","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2601.15348","title":"Abusive music and song transformation using GenAI and LLMs","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.21476","title":"A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.09187","title":"The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN","created":"2026-03-10","cited_by_count":0,"area":null}],"next_cursor":"100"}