SyncAI.news, a Varaisys broadcasting
Improving Audiovisual Speech Recognition through Synthetic Visual Data Augmentation
PB

Pol Buitrago, Pol G\`alvez, Javier Hernando

· 1 min read

ResearcharXiv cs.CL

Improving Audiovisual Speech Recognition through Synthetic Visual Data Augmentation

arXiv:2609.31961v1 Announce Type: cross Abstract: Audiovisual Speech Recognition (AVSR) is a multimodal approach to speech recognition that incorporates visual information from lip movements to enhance model performance. Despite its advantages, its development remains constrained by the limited availability of labeled audiovisual (AV) datasets. This work explores the use of synthetic visual data as a solution, using an audio-driven talking-head pipeline to generate lip-synchronized visual content from existing audio data. We evaluate the effectiveness of synthetic visual data both as an augmentation strategy and as a standalone training resource, applying our approach to Spanish and Catalan. Our results show that augmenting real AV data with synthetic samples yields relative Word Error Rate (WER) reductions of up to 16.2%, demonstrating the potential of this approach. Moreover, we demonstrate that synthetic data alone can serve as a baseline for AVSR training in languages lacking AV datasets. These findings provide evidence that synthetic visual data can serve as a scalable solution to AVSR data scarcity, enabling broader language coverage.

Original source

This story was published by arXiv cs.CL and written by Pol Buitrago, Pol G\`alvez, Javier Hernando. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News