mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rouditchenko, Andrew, Thomas, Samuel, Kuehne, Hilde, Feris, Rogerio, Glass, James
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915276032835584
author Rouditchenko, Andrew
Thomas, Samuel
Kuehne, Hilde
Feris, Rogerio
Glass, James
author_facet Rouditchenko, Andrew
Thomas, Samuel
Kuehne, Hilde
Feris, Rogerio
Glass, James
contents Audio-Visual Speech Recognition (AVSR) combines lip-based video with audio and can improve performance in noise, but most methods are trained only on English data. One limitation is the lack of large-scale multilingual video data, which makes it hard to train models from scratch. In this work, we propose mWhisper-Flamingo for multilingual AVSR which combines the strengths of a pre-trained audio model (Whisper) and video model (AV-HuBERT). To enable better multi-modal integration and improve the noisy multilingual performance, we introduce decoder modality dropout where the model is trained both on paired audio-visual inputs and separate audio/visual inputs. mWhisper-Flamingo achieves state-of-the-art WER on MuAViC, an AVSR dataset of 9 languages. Audio-visual mWhisper-Flamingo consistently outperforms audio-only Whisper on all languages in noisy conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2502_01547
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
Rouditchenko, Andrew
Thomas, Samuel
Kuehne, Hilde
Feris, Rogerio
Glass, James
Audio and Speech Processing
Computer Vision and Pattern Recognition
Sound
Audio-Visual Speech Recognition (AVSR) combines lip-based video with audio and can improve performance in noise, but most methods are trained only on English data. One limitation is the lack of large-scale multilingual video data, which makes it hard to train models from scratch. In this work, we propose mWhisper-Flamingo for multilingual AVSR which combines the strengths of a pre-trained audio model (Whisper) and video model (AV-HuBERT). To enable better multi-modal integration and improve the noisy multilingual performance, we introduce decoder modality dropout where the model is trained both on paired audio-visual inputs and separate audio/visual inputs. mWhisper-Flamingo achieves state-of-the-art WER on MuAViC, an AVSR dataset of 9 languages. Audio-visual mWhisper-Flamingo consistently outperforms audio-only Whisper on all languages in noisy conditions.
title mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
topic Audio and Speech Processing
Computer Vision and Pattern Recognition
Sound
url https://arxiv.org/abs/2502.01547