# Speech2Face: Learning the Face Behind a Voice Source: [Speech2Face: Learning the Face Behind a Voice]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:34:37.515Z Authors: Tae-Hyun Oh, Tali Dekel, Changil Kim, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Wojciech Matusik Published: 2019-05-23T16:54:17.000Z ## Abstract How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of faces and speech in Internet videos, without the need to model attributes explicitly. We evaluate and numerically quantify how--and in what manner--our Speech2Face reconstructions, obtained directly from audio, resemble the true face images of the speakers. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Speech-to-Portrait on AVSpeech (test)](): Speech-to-Portrait; AVSpeech (test); L1 Error: 67.18. - [Speech-to-Portrait on VoxCeleb (test)](): Speech-to-Portrait; VoxCeleb (test); L1 Error: 66.46. ## Original sources and implementation [Original paper]() [PDF]()