{"total":31,"rows":[{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2405.18386","title":"Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning","created":"2024-05-28","cited_by_count":15,"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":"2310.00140","title":"GASS: Generalizing Audio Source Separation with Large-scale Data","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","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":"2409.11228","title":"Learning Source Disentanglement in Neural Audio Codec","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2404.01740","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2407.11277","title":"Target conversation extraction: Source separation using turn-taking dynamics","created":"2024-07-15","cited_by_count":4,"area":null},{"id":"2509.18606","title":"FlexSED: Towards Open-Vocabulary Sound Event Detection","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2507.03273","title":"Event2Audio: Event-Based Optical Vibration Sensing","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2510.09065","title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2409.12415","title":"Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues","created":"2024-09-19","cited_by_count":2,"area":null},{"id":"2506.01015","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2506.20995","title":"Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2508.03041","title":"Neural Speech Extraction with Human Feedback","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2407.11745","title":"Universal Sound Separation with Self-Supervised Audio Masked Autoencoder","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2408.09269","title":"Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2410.12028","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","created":"2024-10-15","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":"2601.19702","title":"SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2607.02343","title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.24821","title":"AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2406.11248","title":"Performance Improvement of Language-Queried Audio Source Separation Based on Caption Augmentation From Large Language Models for DCASE Challenge 2024 Task 9","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2410.03904","title":"Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2505.21025","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2601.12594","title":"SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2603.14803","title":"VorTEX: Various overlap ratio for Target speech EXtraction","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2609.36577","title":"Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}