Tailored Design of Audio-Visual Speech Recognition Models using Branchformers

TL;DR

This paper introduces a flexible, parameter-efficient audio-visual speech recognition framework using Branchformer architectures, achieving state-of-the-art results with reduced complexity on English and Spanish benchmarks.

Contribution

It is the first to apply encoder architectures like Branchformer to design tailored, interpretable AVSR systems that outperform existing models in accuracy and efficiency.

Findings

Achieved approximately 2.5% WER on English AVSR benchmark.

Surpassed existing approaches for Spanish AVSR, establishing a new benchmark.

Reduced model complexity while maintaining state-of-the-art recognition rates.

Abstract

Recent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed through the design of models composed of two independent encoders, each dedicated to a specific modality. However, while recent works have explored unified audio-visual encoders, determining the optimal cross-modal architecture remains an ongoing challenge. Furthermore, such approaches often rely on models comprising vast amounts of parameters and high computational cost training processes. In this paper, we aim to bridge this research gap by introducing a novel audio-visual framework. Our proposed method constitutes, to the best of our knowledge, the first attempt to harness the flexibility and interpretability offered by encoder architectures, such as the Branchformer, in the design of parameter-efficient AVSR systems. To be more precise, the proposed framework consists of two steps: first, estimating audio- and video-only systems, and then designing a tailored audio-visual unified encoder based on the layer-level branch scores provided by the modality-specific models. Extensive experiments on English and Spanish AVSR benchmarks covering multiple data conditions and scenarios demonstrated the effectiveness of our proposed method. Even when trained on a moderate scale of data, our models achieve competitive word error rates (WER) of approximately 2.5\% for English and surpass existing approaches for Spanish, establishing a new benchmark with an average WER of around 9.1\%. These results reflect how our tailored AVSR system is able to reach state-of-the-art recognition rates while significantly reducing the model complexity w.r.t. the prevalent approach in the field. Code and pre-trained models are available at https://github.com/david-gimeno/tailored-avsr.