A Multi-View Approach To Audio-Visual Speaker Verification

Although speaker verification has conventionally been an audio-only task, some practical applications provide both audio and visual streams of input. In these cases, the visual stream provides complementary information and can often be leveraged in conjunction with the acoustics of speech to improve...

Full description

Saved in:
Bibliographic Details
Main Authors Sarı, Leda, Singh, Kritika, Zhou, Jiatong, Torresani, Lorenzo, Singhal, Nayan, Saraf, Yatharth
Format Journal Article
LanguageEnglish
Published 11.02.2021
Subjects
Computer Science - Learning
Computer Science - Sound
Online AccessGet full text

Cover

More Information
Summary:Although speaker verification has conventionally been an audio-only task, some practical applications provide both audio and visual streams of input. In these cases, the visual stream provides complementary information and can often be leveraged in conjunction with the acoustics of speech to improve verification performance. In this study, we explore audio-visual approaches to speaker verification, starting with standard fusion techniques to learn joint audio-visual (AV) embeddings, and then propose a novel approach to handle cross-modal verification at test time. Specifically, we investigate unimodal and concatenation based AV fusion and report the lowest AV equal error rate (EER) of 0.7% on the VoxCeleb1 dataset using our best system. As these methods lack the ability to do cross-modal verification, we introduce a multi-view model which uses a shared classifier to map audio and video into the same space. This new approach achieves 28% EER on VoxCeleb1 in the challenging testing condition of cross-modal verification.
DOI:10.48550/arxiv.2102.06291