{"total":112,"rows":[{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42,"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":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2507.08557","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2412.19351","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models","created":"2024-12-26","cited_by_count":17,"area":null},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2510.00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model","created":"2025-09-27","cited_by_count":14,"area":null},{"id":"2510.03117","title":"Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction","created":"2025-10-03","cited_by_count":11,"area":null},{"id":"2601.02731","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","created":"2026-01-06","cited_by_count":11,"area":null},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2508.04651","title":"Live Music Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2601.04151","title":"Apollo: Unified Multi-Task Audio-Video Joint Generation","created":"2026-01-07","cited_by_count":10,"area":null},{"id":"2505.19314","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2412.20378","title":"Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control","created":"2024-12-29","cited_by_count":8,"area":null},{"id":"2507.20900","title":"Music Arena: Live Evaluation for Text-to-Music","created":"2025-07-28","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":"2507.03599","title":"MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI","created":"2025-07-04","cited_by_count":7,"area":null},{"id":"2511.13219","title":"FoleyBench: A Benchmark For Video-to-Audio Models","created":"2025-11-17","cited_by_count":7,"area":null},{"id":"2512.07209","title":"Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2410.13754","title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2410.17589","title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation","created":"2024-10-23","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":"2505.17613","title":"MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2512.24731","title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","created":"2025-12-31","cited_by_count":6,"area":null},{"id":"2603.22677","title":"MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2502.04230","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2505.16195","title":"SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2509.23727","title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2510.02110","title":"SoundReactor: Frame-level Online Video-to-Audio Generation","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2501.05631","title":"HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection","created":"2025-01-10","cited_by_count":4,"area":null},{"id":"2503.21254","title":"Vision-to-Music Generation: A Survey","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2510.21581","title":"Foley Control: Aligning a Frozen Latent Text-to-Audio Model to Video","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2512.02650","title":"Hear What Matters! Text-conditioned Selective Video-to-Audio Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2605.06407","title":"WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.18613","title":"SAME: A Semantically-Aligned Music Autoencoder","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2412.09405","title":"Learned Compression for Compressed Learning","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2506.18488","title":"AI-Generated Song Detection via Lyrics Transcripts","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2602.03023","title":"Rethinking Music Captioning with Music Metadata LLMs","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.06823","title":"AI-Generated Music Detection in Broadcast Monitoring","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.04366","title":"Low-Resource Guidance for Controllable Latent Audio Diffusion","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2504.03329","title":"Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.03530","title":"How Far Are We from Generating Missing Modalities with Foundation Models?","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2509.08283","title":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","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":"2510.23530","title":"Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2510.25228","title":"'Studies for': A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2602.09891","title":"Stemphonic: All-at-once Flexible Multi-stem Music Generation","created":"2026-02-10","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":"2604.05731","title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.01790","title":"Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2605.03929","title":"PHALAR: Phasors for Learned Musical Audio Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.15831","title":"Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.05177","title":"MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.15186","title":"FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2607.09091","title":"Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.11576","title":"Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.30940","title":"MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative Music AI","created":"2026-08-31","cited_by_count":1,"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":"2410.16785","title":"Annotation-Free MIDI-to-Audio Synthesis via Concatenative Synthesis and Generative Refinement","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2509.00813","title":"AImoclips: A Benchmark for Evaluating Emotion Conveyance in Text-to-Music Generation","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.12581","title":"Exploring Training Data Attribution under Limited Access Constraints","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.02916","title":"SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.05828","title":"StereoSync: Spatially-Aware Stereo Audio Generation from Video","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.05829","title":"FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.15895","title":"BREATH: A Bio-Radar Embodied Agent for Tonal and Human-Aware Diffusion Music Generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2511.05350","title":"Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.07205","title":"Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2602.02591","title":"VividVoice: A Unified Framework for Scene-Aware Visually-Driven Speech Synthesis","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.08233","title":"Tutti: Expressive Multi-Singer Synthesis via Structure-Level Timbre Control and Vocal Texture Modeling","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.15082","title":"S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.15909","title":"Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.01101","title":"SyncTrack: Rhythmic Stability and Synchronization in Multi-Track Music Generation","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.23667","title":"Echoes: A semantically-aligned music deepfake detection dataset","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.17986","title":"Latent Fourier Transform","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.06628","title":"LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08794","title":"Deterministic Decomposition of Stochastic Generative Dynamics","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.09259","title":"Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.14555","title":"Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.28063","title":"Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.01703","title":"JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.05852","title":"UniVoice: A Unified Model for Speech and Singing Voice Generation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.07387","title":"Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.24307","title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.27320","title":"Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08526","title":"A Quantized Native Runtime for On-Device Semantic Audio Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.08545","title":"Structural Bottlenecks on Frequency Representation in End-to-End Audio Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.09973","title":"A Production-Oriented Framework for Evaluation of SFX Generation","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":"100"}