Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation

• URL: http://arxiv.org/abs/2605.25195v2
• Date: Mon, 01 Jun 2026 01:54:28 GMT
• Title: Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
• Abstract summary: Baton is a framework that introduces explicit semantic planning into joint video-audio generation.<n>Our key insight is that complementing coarse text guidance with semantically rich, modality-aware planned tokens, can simultaneously restore fine-grained semantic detail.<n> experiments on benchmarks show the effectiveness of Baton both qualitatively and quantitatively.
• Score: 113.24577778437295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cause is that existing methods rely on coarse text embeddings from off-the-shelf encoders to guide audio-video denoising, which discards fine-grained semantics and, critically, lacks a shared long-horizon plan, leading to uncoordinated denoising trajectories and fragile cross-modal alignment. We propose Baton, the first framework that introduces explicit semantic planning into joint video-audio generation. Our key insight is that complementing coarse text guidance with semantically rich, modality-aware planned tokens, jointly reasoned and mutually aligned before denoising, can simultaneously restore fine-grained semantic detail and establish a shared blueprint that coordinates both audio and video denoising trajectories. Concretely, Baton first introduces the VA-Planner, a multimodal language model equipped with dual semantic alignment towers, where learnable queries cross-attend to both video and audio features to produce a pair of semantically aligned video and audio planned tokens as keyframe-level blueprints. These planned tokens are injected into the diffusion backbone via cross-attention layers, providing temporally grounded guidance complementary to coarse text embeddings. Since planned tokens do not share one-to-one spatial-temporal correspondence with diffusion latents, we further propose Relative Semantic RoPE, a relative positional encoding that maps planned tokens and latents into a shared spatial-temporal coordinate frame, enabling each latent to accurately attend to its positionally corresponding semantic cues. Experiments on benchmarks show the effectiveness of Baton both qualitatively and quantitatively.

Related papers

• TimeSteer: Inference-Time Speech Scheduling in Joint Audio-Visual Diffusion Models [49.44322041671119]
  emphinference-time speech scheduling is a novel task that places coupled speech and visual articulation within user-specified begin--end intervals.<n>We propose textbfTimeSteer, a training-free framework that localizes each utterance's source span.<n>TimeSteer substantially improves interval controllability over training-free baselines while maintaining competitive overall generation quality.
  arXiv  Detail & Related papers  (2026-09-01T14:12:57Z)
• OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation [73.57253966578186]
  We present OmniVAE, a jointly trained audio-video VAE that learns fine-grained semantic alignment between audio and video latent representations.<n>Experiments show that both objectives consistently improve the learnability of the latent spaces.
  arXiv  Detail & Related papers  (2026-07-26T21:51:28Z)
• Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization [69.67186845167568]
  Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events.<n>Existing methods primarily learn joint audio-visual representations in Euclidean space.<n>We propose a hierarchical semantic constrained heterogeneous graph (HSCHG) for audio-visual event localization framework.
  arXiv  Detail & Related papers  (2026-06-05T08:23:58Z)
• Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation [50.411841997631484]
  We present Unison, a unified framework that promotes coherence across the motion, speech, and sound modalities.<n>We show that Unison achieves state-of-the-art performance in both audio perceptual quality and cross-modal synchronization.
  arXiv  Detail & Related papers  (2026-05-09T06:32:54Z)
• Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection [24.57005070272218]
  Open-Vocabulary Temporal Action Detection (OV-TAD) aims to localize and classify action segments of unseen videos.<n> DFAlign is the first framework that leverages diffusion-based denoising to generate foreground knowledge for the guidance of action-video alignment.<n>Our method achieves state-of-the-art performance on two OV-TAD benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T14:18:27Z)
• Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization [1.1242490155213278]
  HILBERT is a cross-attentive framework for learning document-level audio-text representations.<n>We show that HILBERT learns semantically meaningful long-sequence representations and achieves superior performance on highly imbalanced multi-class settings.
  arXiv  Detail & Related papers  (2026-04-17T17:07:35Z)
• CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing [76.74048814837336]
  Movie dubbing aims to synthesize speech that preserves the vocal identity of a reference audio while synchronizing with the lip movements in a target video.<n>Existing methods fail to achieve precise lip-sync and lack naturalness due to explicit alignment at the duration level.<n>We propose a novel flow matching-based movie dubbing framework driven by the Cognitive Synchronous Diffusion Transformer (CoSync-DiT)
  arXiv  Detail & Related papers  (2026-04-14T05:03:57Z)
• TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding [15.908533215017059]
  We present TagSpeech, a unified framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization.<n>The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that acts as a synchronization signal between semantic understanding and speaker tracking.
  arXiv  Detail & Related papers  (2026-01-11T12:40:07Z)
• Implicit Counterfactual Learning for Audio-Visual Segmentation [50.69377287012591]
  We propose the implicit counterfactual framework (ICF) to achieve unbiased cross-modal understanding.<n>Due to the lack of semantics, heterogeneous representations may lead to erroneous matches.<n>We introduce the multi-granularity implicit text (MIT) involving video-, segment- and frame-level as the bridge to establish the modality-shared space.
  arXiv  Detail & Related papers  (2025-07-28T11:46:35Z)
• Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation [0.9285295512807729]
  We propose a data augmentation technique for generating hallucinated audio captions and show that similarity based on an audio-text shared latent space is suitable for detecting hallucination. We then propose a parameter efficient inference time faithful decoding algorithm that enables smaller audio captioning models with performance equivalent to larger models trained with more data.
  arXiv  Detail & Related papers  (2023-09-06T19:42:52Z)
• Unsupervised Sound Localization via Iterative Contrastive Learning [106.56167882750792]
  We propose an iterative contrastive learning framework that requires no data annotations. We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video. Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio.
  arXiv  Detail & Related papers  (2021-04-01T07:48:29Z)
• Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis [59.623780036359655]
  Articulatory-to-acoustic (A2A) synthesis refers to the generation of audible speech from captured movement of the speech articulators. This technique has numerous applications, such as restoring oral communication to people who cannot longer speak due to illness or injury. We propose a solution to this problem based on the theory of multi-view learning.
  arXiv  Detail & Related papers  (2020-12-30T15:09:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.