{"total":59,"rows":[{"id":"2504.18425","title":"Kimi-Audio Technical Report","created":"2025-04-25","cited_by_count":222,"area":null},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31,"area":null},{"id":"2410.01469","title":"TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2308.16892","title":"ReZero: Region-customizable Sound Extraction","created":"2023-08-31","cited_by_count":10,"area":null},{"id":"2312.03464","title":"Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference","created":"2023-12-06","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":"2409.08514","title":"Apollo: Band-sequence Modeling for High-Quality Audio Restoration","created":"2024-09-13","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":"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":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2404.04947","title":"Gull: A Generative Multifunctional Audio Codec","created":"2024-04-07","cited_by_count":5,"area":null},{"id":"2505.21827","title":"Music Source Restoration","created":"2025-05-27","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":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2305.16189","title":"Multi-scale clustering and source separation of InSight mission seismic data","created":"2023-05-25","cited_by_count":3,"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":"2505.08694","title":"A Survey of Deep Learning for Complex Speech Spectrograms","created":"2025-05-13","cited_by_count":3,"area":null},{"id":"2601.13802","title":"Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2309.17189","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","created":"2023-09-29","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":"2503.10287","title":"MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment","created":"2025-03-13","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":"2509.14052","title":"AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck","created":"2025-09-17","cited_by_count":2,"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":"2310.04369","title":"MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2401.06203","title":"Remixing Music for Hearing Aids Using Ensemble of Fine-Tuned Source Separators","created":"2024-01-11","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":"2410.20773","title":"An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2504.17782","title":"Unleashing the Power of Natural Audio Featuring Multiple Sound Sources","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2505.19534","title":"Training-Free Multi-Step Audio Source Separation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.09307","title":"Target speaker anonymization in multi-speaker recordings","created":"2025-10-10","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":"2601.04343","title":"Summary of The Inaugural Music Source Restoration Challenge","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2607.11096","title":"Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decoder","created":"2026-07-13","cited_by_count":1,"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":"2305.01758","title":"Adversarial Generative NMF for Single Channel Source Separation","created":"2023-04-24","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":"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":"2501.03689","title":"MAJL: A Model-Agnostic Joint Learning Framework for Music Source Separation and Pitch Estimation","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2504.21772","title":"Solving Copyright Infringement on Short Video Platforms: Novel Datasets and an Audio Restoration Deep Learning Pipeline","created":"2025-04-30","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":"2509.15666","title":"TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2509.18561","title":"SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes","created":"2025-09-23","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":"2510.10687","title":"LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation","created":"2025-10-12","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":"2601.19533","title":"SLM-SS: Speech Language Model for Generative Speech Separation","created":"2026-01-27","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},{"id":"2605.14765","title":"Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.24127","title":"DTT-BSR+: A Generative-Regression Cascade for Music Source Restoration","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.07226","title":"Iterative Audio Separation with Mixture Consistency via MIMO Model Extension","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.33265","title":"SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01619","title":"Exposing the Cost of Deep Learning Audio Development","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}