FaceFilter: Audio-visual speech separation using still images
This method provides a practical solution for speech separation with unseen speakers, applicable in platforms where user profile images are available, though it is incremental as it builds on existing audio-visual separation techniques.
The paper tackles the problem of separating a target speaker's speech from a mixture using a deep audio-visual network, achieving strong qualitative and quantitative results by using a single face image as a conditional feature instead of lip movement or pre-enrolled speaker data.
The objective of this paper is to separate a target speaker's speech from a mixture of two speakers using a deep audio-visual speech separation network. Unlike previous works that used lip movement on video clips or pre-enrolled speaker information as an auxiliary conditional feature, we use a single face image of the target speaker. In this task, the conditional feature is obtained from facial appearance in cross-modal biometric task, where audio and visual identity representations are shared in latent space. Learnt identities from facial images enforce the network to isolate matched speakers and extract the voices from mixed speech. It solves the permutation problem caused by swapped channel outputs, frequently occurred in speech separation tasks. The proposed method is far more practical than video-based speech separation since user profile images are readily available on many platforms. Also, unlike speaker-aware separation methods, it is applicable on separation with unseen speakers who have never been enrolled before. We show strong qualitative and quantitative results on challenging real-world examples.