{"total":31,"rows":[{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2402.12636","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","created":"2024-02-20","cited_by_count":21,"area":null},{"id":"2212.12137","title":"Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing","created":"2022-12-23","cited_by_count":17,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2403.01087","title":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","created":"2024-03-02","cited_by_count":7,"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":"2408.11593","title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2302.12979","title":"Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing","created":"2023-02-25","cited_by_count":5,"area":null},{"id":"2306.17005","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2305.13204","title":"Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters","created":"2023-05-22","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":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","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":"2412.20359","title":"EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2511.12150","title":"Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2407.06174","title":"The Tug-of-War Between Deepfake Generation and Detection","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2205.12194","title":"Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel's Weekly Video Podcasts","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2412.16530","title":"Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation","created":"2024-12-21","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":"2509.12959","title":"Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2512.05126","title":"SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2603.19831","title":"Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.09111","title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2606.16009","title":"Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2609.26486","title":"Not Quite My Tempo: Voice Activity-aware Speech Synthesis for Lip-Synchronous Dubbing","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}