The reviewed record of science sign in
Pith

arxiv: 2110.08791 · v1 · pith:DFH6ZZ5E · submitted 2021-10-17 · cs.CV · cs.AI· cs.LG· cs.SD· eess.AS

Taming Visually Guided Sound Generation

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DFH6ZZ5Erecord.jsonopen to challenge →

classification cs.CV cs.AIcs.LGcs.SDeess.AS
keywords generatedgenerationmetricsmodelsamplessamplingspectrogramaudio
0
0 comments X
read the original abstract

Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we propose a single model capable of generating visually relevant, high-fidelity sounds prompted with a set of frames from open-domain videos in less time than it takes to play it on a single GPU. We train a transformer to sample a new spectrogram from the pre-trained spectrogram codebook given the set of video features. The codebook is obtained using a variant of VQGAN trained to produce a compact sampling space with a novel spectrogram-based perceptual loss. The generated spectrogram is transformed into a waveform using a window-based GAN that significantly speeds up generation. Considering the lack of metrics for automatic evaluation of generated spectrograms, we also build a family of metrics called FID and MKL. These metrics are based on a novel sound classifier, called Melception, and designed to evaluate the fidelity and relevance of open-domain samples. Both qualitative and quantitative studies are conducted on small- and large-scale datasets to evaluate the fidelity and relevance of generated samples. We also compare our model to the state-of-the-art and observe a substantial improvement in quality, size, and computation time. Code, demo, and samples: v-iashin.github.io/SpecVQGAN

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 5 Pith papers

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

  1. AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models

    cs.AI 2026-05 unverdicted novelty 7.0

    AVBench is a benchmark for human-centric AV generation evaluation featuring ten fine-grained dimensions and preference-learned evaluators that output continuous probabilistic scores from binary decisions.

  2. InstructAV2AV: Instruction-Guided Audio-Video Joint Editing

    cs.CV 2026-05 unverdicted novelty 7.0

    InstructAV2AV is an end-to-end instruction-guided audio-video joint editing model that adapts a pre-trained backbone with gated attention and two-stage training, outperforming prior methods on 11 metrics after buildin...

  3. AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing

    cs.SD 2026-05 unverdicted novelty 6.0

    AnchorSteer couples self-discovered semantic concept vectors with structural anchoring in diffusion models to achieve controllable music editing with preserved structure.

  4. Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

    cs.CV 2026-02 unverdicted novelty 6.0

    MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.

  5. Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

    eess.AS 2026-05 unverdicted novelty 4.0

    SwanSphere introduces a causal autoregressive diffusion transformer architecture with SVAC contrastive learning and ODPO optimization for streaming spatial audio generation from video and text.