SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.12233 · 2024

SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual Speech Recognition (VSR) stands at the intersection of computer vision and speech recognition, aiming to interpret spoken content from visual cues. A prominent challenge in VSR is the presence of homophenes-visually similar lip gestures that represent different phonemes. Prior approaches have sought to distinguish fine-grained visemes by aligning visual and auditory semantics, but often fell short of full synchronization. To address this, we present SyncVSR, an end-to-end learning framework that leverages quantized audio for frame-level crossmodal supervision. By integrating a projection layer that synchronizes visual representation with acoustic data, our encoder learns to generate discrete audio tokens from a video sequence in a non-autoregressive manner. SyncVSR shows versatility across tasks, languages, and modalities at the cost of a forward pass. Our empirical evaluations show that it not only achieves state-of-the-art results but also reduces data usage by up to ninefold.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.12233")
get_code_for_paper("2406.12233")
have("2406.12233")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.12233.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.12233.svg)](https://syntology.ai/paper/2406.12233)

Connect an agent — have() is free.