Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning

Abstract

We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on Perception Encoder, PE-AV makes several key contributions to extend representations to audio, and natively support joint embeddings across audio–video, audio–text, and video–text modalities. PE-AV’s unified cross-modal embeddings enable novel tasks such as speech retrieval, and set a new state of the art across standard audio and video benchmarks. We unlock this by building a strong audiovisual data engine that synthesizes high-quality captions for O(100M) audio–video pairs, enabling large-scale supervision consistent across modalities. Our audio data includes speech, music, and general sound effects—avoiding single-domain limitations common in prior work. We exploit ten pairwise contrastive objectives, showing that scaling cross-modality and caption-type pairs strengthens alignment and improves zero-shot performance. We further develop PE-A-Frame by fine-tuning PE-AV with frame-level contrastive objectives, enabling fine-grained audio-frame-to-text alignment for tasks such as sound event detection. Code: https://github.com/facebookresearch/perception_models. Model: https://huggingface.co/collections/facebook/perception-encoder-audio-visual