The paper investigates how sequence design influences temporal synchronization in unified decoder-only transformers for video‑text‑to‑speech synthesis. By training a Visatronic model on VoxCeleb2, the authors compare positional encoding schemes and modality ordering, finding that global sequential indexing and co‑temporal ordered indexing yield similar in‑domain performance, while text‑first co‑temporal indexing best transfers under domain shift. They also introduce TimeSync, a phoneme‑level metric that uncovers misalignments missed by frame‑level measures, and demonstrate that text and video provide complementary cues for intelligibility and temporal/emotional expressiveness.
arXiv:2606. 01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos.
arXiv:2604.15086v3 Announce Type: replace-cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-gra...
Vorch-Human is a unified framework for human‑centric audio‑visual generation that handles multiple tasks—animating a person from speech, jointly generating speech and video from a voice reference, and synthesizing a scene from paired appearance and voice references—using a single dual‑stream audio‑video diffusion transformer. The model incorporates clean condition‑audio and condition‑video tokens, per‑token task embeddings, temporal position types, condition masks, and a shared multimodal prompt encoder to express diverse inputs such as driving speech, timbre examples, first frames, and subject images. A two‑level data pipeline supplies the necessary supervision by extracting speech, appearance, and timbre annotations from clips and linking consistent identity and outfit references across videos, while a frozen‑prefix recurrence enables long‑form audio‑driven generation with reduced boundary discontinuity and identity drift.
The paper introduces Alignment-Free Text‑Audiobox (Text‑AB), a unified diffusion‑based framework that performs high‑quality voice dubbing and full‑duplex dialogue synthesis without requiring forced alignment. Text‑AB uses a latent diffusion model with DAC‑VAE features, achieving over 10× compression compared to prior EnCodec representations, and learns text‑speech alignment via cross‑attention. The authors pretrain a 3B‑parameter model on 480k hours of monolingual speech and fine‑tune it for cross‑lingual dubbing, full‑duplex dialogue, and emotional dialogue, reporting significant improvements in prosody, voice similarity, naturalness, and emotional expressivity over existing internal systems.
arXiv:2506. 10915v2 Announce Type: replace-cross Abstract: Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators.
SyncVoice is a new automatic video dubbing framework that adds a lightweight Text‑Visual Fusion Module to a pretrained TTS system, aligning visual features with linguistic representations to produce temporally synchronized speech. The approach avoids complex architectural changes and achieves state‑of‑the‑art performance on the LRS3 dataset in zero‑shot dubbing. When further trained on a large bilingual audio‑visual corpus, SyncVoice improves vocal fidelity while maintaining synchronization, enabling a single model to dub both Chinese and English videos.
PVSync is a unified model that estimates audio‑visual offset and scores phoneme‑level articulation for lip‑sync tasks. It uses window‑level contrastive learning for synchronisation and a phoneme‑level articulation objective that aligns audio and video embeddings of the same viseme class across clips. The model achieves higher correlation with human rankings and better performance on offset recovery and viseme matching benchmarks compared to existing methods.
The paper introduces MOCO, a diffusion-based framework that generates 3D avatar motions from concurrent multimodal inputs such as speech audio, text descriptions, and trajectory data. MOCO decouples motion generation by independently producing modality-specific motions at each denoising step and then assembling them according to spatial rules, iteratively refining the combined motion. This approach yields coherent, lifelike, and synchronized movements, outperforming existing baselines on a multimodal benchmark.
arXiv:2609.00505v1 Announce Type: new Abstract: Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues...
TimeSteer introduces inference‑time speech scheduling for joint audio‑visual diffusion models, enabling users to place speech and visual articulation within specified time intervals without fine‑tuning the backbone. The method leverages two properties of the denoising process: a timing‑sensitive text‑to‑audio cross‑attention head that reveals each utterance’s source span, and a predicted clean latent that already organizes coupled speech and visual content. TimeSteer localizes each utterance’s source span and remaps the associated audio‑visual latent to the target interval, and the authors present SpeechShift as the first benchmark for interval‑level speech scheduling.
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
The paper introduces Modality Self-Play (MSP), a training framework that enables multimodal large language models to learn cross‑modal interactions without requiring paired non‑text data. MSP uses proxy‑mediated textual descriptions of unseen modalities as semantic bridges, allowing a model to generate and align these proxies with observed modalities. Experiments show that MSP achieves state‑of‑the‑art or competitive performance on several multimodal benchmarks and demonstrates effective zero‑shot modality composition through learned bridges and anchor‑supporting proxy descriptions.