Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning


Abstract

We present a generative adversarial network to synthesize 3D pose sequences of co-speech upper-body gestures with appropriate affective expressions. Our network consists of a generator, which synthesizes gestures from a joint embedding space of features encoded from the input speech and the seed poses, and a discriminator, which distinguishes between the synthesized pose sequences and real 3D pose sequences. We leverage the mel-frequency cepstral coefficients and the text transcript computed from the input speech in separate encoders in our generator to learn the desired sentiments and the associated affective cues. We design an affective encoder using multi-scale spatial-temporal graph convolutions to transform 3D pose sequences into latent, pose-based affective features. We use our affective encoder both in our generator, where it learns affective features from the seed poses to guide the gesture synthesis, and in our discriminator, where it enforces the synthesized gestures to contain the appropriate affective expressions. We perform extensive evaluations on two benchmark datasets for gesture synthesis from the speech, the TED Gesture Dataset and the GENEA Challenge 2020 Dataset. Compared to the best baselines, we improve the mean absolute joint error by 10—33%, the mean acceleration difference by 8—58%, and the Fréchet Gesture Distance by 21—34%. We also conduct a user study and observe that compared to the best current baselines, around 15.28% of participants indicated our synthesized gestures appear more plausible, and around 16.32% of participants felt the gestures had more appropriate affective expressions aligned with the speech.

Video

Paper

Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning.
Uttaran Bhattacharya, Elizabeth Childs, Nicholas Rewkowski, Dinesh Manocha

Code

https://github.com/UttaranB127/speech2affective_gestures