Pith. sign in

REVIEW 7 cited by

From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.19132 v1 pith:AOFVIHTT submitted 2024-09-27 cs.MM cs.CVcs.LGcs.SDeess.AS

From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation

classification cs.MM cs.CVcs.LGcs.SDeess.AS
keywords audioaudio-visualrepresentationlearningvisualfeaturesgenerationmodalities
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Video encompasses both visual and auditory data, creating a perceptually rich experience where these two modalities complement each other. As such, videos are a valuable type of media for the investigation of the interplay between audio and visual elements. Previous studies of audio-visual modalities primarily focused on either audio-visual representation learning or generative modeling of a modality conditioned on the other, creating a disconnect between these two branches. A unified framework that learns representation and generates modalities has not been developed yet. In this work, we introduce a novel framework called Vision to Audio and Beyond (VAB) to bridge the gap between audio-visual representation learning and vision-to-audio generation. The key approach of VAB is that rather than working with raw video frames and audio data, VAB performs representation learning and generative modeling within latent spaces. In particular, VAB uses a pre-trained audio tokenizer and an image encoder to obtain audio tokens and visual features, respectively. It then performs the pre-training task of visual-conditioned masked audio token prediction. This training strategy enables the model to engage in contextual learning and simultaneous video-to-audio generation. After the pre-training phase, VAB employs the iterative-decoding approach to rapidly generate audio tokens conditioned on visual features. Since VAB is a unified model, its backbone can be fine-tuned for various audio-visual downstream tasks. Our experiments showcase the efficiency of VAB in producing high-quality audio from video, and its capability to acquire semantic audio-visual features, leading to competitive results in audio-visual retrieval and classification.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Do Joint Audio-Video Generation Models Understand Physics?

    cs.SD 2026-05 unverdicted novelty 7.0

    Current joint audio-video generation models lack robust physical commonsense, especially during transitions and when prompted for impossible behaviors.

  2. Do Joint Audio-Video Generation Models Understand Physics?

    cs.SD 2026-05 unverdicted novelty 7.0

    AV-Phys Bench shows that current joint audio-video models lack robust physical commonsense, with major drops on transitions and deliberate anti-physics prompts.

  3. AudioMoG: Guiding Audio Generation with Mixture-of-Guidance

    cs.SD 2025-09 unverdicted novelty 7.0

    AudioMoG is a mixture-of-guidance sampling technique that combines CFG and AG signals to outperform single-guidance baselines in text-to-audio generation at equivalent speed.

  4. Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning

    cs.SD 2026-04 unverdicted novelty 6.0

    TG-DP decouples reconstruction and alignment objectives into separate paths with teacher guidance on visibility patterns, yielding SOTA zero-shot audio-video retrieval gains on AudioSet.

  5. AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

    cs.SD 2026-06 unverdicted novelty 5.0

    A distilled multimodal diffusion model generates audio from text, video, or audio in four steps with claimed superior quality and ~25× fewer function evaluations.

  6. AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

    cs.SD 2026-06 unverdicted novelty 5.0

    AudioX-Turbo distills a Multimodal Diffusion Transformer into a 4-step student model for efficient multimodal anything-to-audio generation, trained on a new 9.2M-sample dataset IF-caps-Pro.

  7. ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals

    eess.AS 2026-04 unverdicted novelty 5.0

    ULTRAS unifies audio and speech representation learning in a single transformer by applying patch masking to log-mel spectrograms and using a joint spectral-temporal prediction loss.