{"total":20,"rows":[{"id":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","cited_by_count":38,"area":null},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2503.12042","title":"Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2408.04535","title":"Synchronous Multi-modal Semantic Communication System with Packet-level Coding","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2503.22265","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2504.05583","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2312.17508","title":"Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion","created":"2023-12-29","cited_by_count":3,"area":null},{"id":"2412.18748","title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2601.14777","title":"FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2411.17690","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2407.04697","title":"VCoME: Verbal Video Composition with Multimodal Editing Effects","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2503.14928","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2505.19119","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2505.22024","title":"RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2306.02568","title":"Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2505.01450","title":"Towards Film-Making Production Dialogue, Narration, Monologue Adaptive Moving Dubbing Benchmarks","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.16279","title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2604.15923","title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2610.05932","title":"UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}