We present a machine learning technique for driving 3D facial animation by audio input in real time and with low latency. Our deep neural network learns a mapping from input waveforms to the 3D vertex coordinates of a face model, and simultaneously discovers a compact, latent code that disambiguates the variations in facial expression that cannot be explained by the audio alone. During inference, the latent code can be used as an intuitive control for the emotional state of the face puppet. We train our network with 3--5 minutes of high-quality animation data obtained using traditional, vision-based performance capture methods. Even though our primary goal is to model the speaking style of a single actor, our model yields reasonable results even when driven with audio from other speakers with different gender, accent, or language, as we demonstrate with a user study. The results are applicable to in-game dialogue, low-cost localization, virtual reality avatars, and telepresence.

Audio-driven facial animation by joint end-to-end learning of pose and emotion

We introduce a simple and effective deep learning approach to automatically generate natural looking speech animation that synchronizes to input speech. Our approach uses a sliding window predictor that learns arbitrary nonlinear mappings from phoneme label input sequences to mouth movements in a way that accurately captures natural motion and visual coarticulation effects. Our deep learning approach enjoys several attractive properties: it runs in real-time, requires minimal parameter tuning, generalizes well to novel input speech sequences, is easily edited to create stylized and emotional speech, and is compatible with existing animation retargeting approaches. One important focus of our work is to develop an effective approach for speech animation that can be easily integrated into existing production pipelines. We provide a detailed description of our end-to-end approach, including machine learning design decisions. Generalized speech animation results are demonstrated over a wide range of animation clips on a variety of characters and voices, including singing and foreign language input. Our approach can also generate on-demand speech animation in real-time from user speech input.

/pdf/a-deep-learning-approach-for-generalized-speech-animation-2xzvv3h1ki.pdf

A deep learning approach for generalized speech animation

Audio-driven 3D facial animation has been widely explored, but achieving realistic, human-like performance is still unsolved. This is due to the lack of available 3D datasets, models, and standard evaluation metrics. To address this, we introduce a unique 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio from 12 speakers. We then train a neural network on our dataset that factors identity from facial motion. The learned model, VOCA (Voice Operated Character Animation) takes any speech signal as input—even speech in languages other than English—and realistically animates a wide range of adult faces. Conditioning on subject labels during training allows the model to learn a variety of realistic speaking styles. VOCA also provides animator controls to alter speaking style, identity-dependent facial shape, and pose (i.e. head, jaw, and eyeball rotations) during animation. To our knowledge, VOCA is the only realistic 3D facial animation model that is readily applicable to unseen subjects without retargeting. This makes VOCA suitable for tasks like in-game video, virtual reality avatars, or any scenario in which the speaker, speech, or language is not known in advance. We make the dataset and model available for research purposes at http://voca.is.tue.mpg.de.

/pdf/capture-learning-and-synthesis-of-3d-speaking-styles-1c1byh77tg.pdf

Capture, Learning, and Synthesis of 3D Speaking Styles

We present a method that generates expressive talking-head videos from a single facial image with audio as the only input. In contrast to previous attempts to learn direct mappings from audio to raw pixels for creating talking faces, our method first disentangles the content and speaker information in the input audio signal. The audio content robustly controls the motion of lips and nearby facial regions, while the speaker information determines the specifics of facial expressions and the rest of the talking-head dynamics. Another key component of our method is the prediction of facial landmarks reflecting the speaker-aware dynamics. Based on this intermediate representation, our method works with many portrait images in a single unified framework, including artistic paintings, sketches, 2D cartoon characters, Japanese mangas, and stylized caricatures. In addition, our method generalizes well for faces and characters that were not observed during training. We present extensive quantitative and qualitative evaluation of our method, in addition to user studies, demonstrating generated talking-heads of significantly higher quality compared to prior state-of-the-art methods.

MakeltTalk: speaker-aware talking-head animation

Speech-driven facial animation is the process that automatically synthesizes talking characters based on speech signals. The majority of work in this domain creates a mapping from audio features to visual features. This approach often requires post-processing using computer graphics techniques to produce realistic albeit subject dependent results. We present an end-to-end system that generates videos of a talking head, using only a still image of a person and an audio clip containing speech, without relying on handcrafted intermediate features. Our method generates videos which have (a) lip movements that are in sync with the audio and (b) natural facial expressions such as blinks and eyebrow movements. Our temporal GAN uses 3 discriminators focused on achieving detailed frames, audio-visual synchronization, and realistic expressions. We quantify the contribution of each component in our model using an ablation study and we provide insights into the latent representation of the model. The generated videos are evaluated based on sharpness, reconstruction quality, lip-reading accuracy, synchronization as well as their ability to generate natural blinks.

/pdf/realistic-speech-driven-facial-animation-with-gans-4wfu2282gn.pdf

Realistic Speech-Driven Facial Animation with GANs

The rich signals we extract from facial expressions imposes high expectations for the science and art of facial animation. While the advent of high-resolution performance capture has greatly improved realism, the utility of procedural animation warrants a prominent place in facial animation workflow. We present a system that, given an input audio soundtrack and speech transcript, automatically generates expressive lip-synchronized facial animation that is amenable to further artistic refinement, and that is comparable with both performance capture and professional animator output. Because of the diversity of ways we produce sound, the mapping from phonemes to visual depictions as visemes is many-valued. We draw from psycholinguistics to capture this variation using two visually distinct anatomical actions: Jaw and Lip, wheresound is primarily controlled by jaw articulation and lower-face muscles, respectively. We describe the construction of a transferable template jali 3D facial rig, built upon the popular facial muscle action unit representation facs. We show that acoustic properties in a speech signal map naturally to the dynamic degree of jaw and lip in visual speech. We provide an array of compelling animation clips, compare against performance capture and existing procedural animation, and report on a brief user study.

JALI: an animator-centric viseme model for expressive lip synchronization

We present a novel deep-learning based approach to producing animator-centric speech motion curves that drive a JALI or standard FACS-based production face-rig, directly from input audio. Our three-stage Long Short-Term Memory (LSTM) network architecture is motivated by psycho-linguistic insights: segmenting speech audio into a stream of phonetic-groups is sufficient for viseme construction; speech styles like mumbling or shouting are strongly co-related to the motion of facial landmarks; and animator style is encoded in viseme motion curve profiles. Our contribution is an automatic real-time lip-synchronization from audio solution that integrates seamlessly into existing animation pipelines. We evaluate our results by: cross-validation to ground-truth data; animator critique and edits; visual comparison to recent deep-learning lip-synchronization solutions; and showing our approach to be resilient to diversity in speaker and language.

Visemenet: audio-driven animator-centric speech animation

We present RigNet, an end-to-end automated method for producing animation rigs from input character models. Given an input 3D model representing an articulated character, RigNet predicts a skeleton that matches the animator expectations in joint placement and topology. It also estimates surface skin weights based on the predicted skeleton. Our method is based on a deep architecture that directly operates on the mesh representation without making assumptions on shape class and structure. The architecture is trained on a large and diverse collection of rigged models, including their mesh, skeletons and corresponding skin weights. Our evaluation is three-fold: we show better results than prior art when quantitatively compared to animator rigs; qualitatively we show that our rigs can be expressively posed and animated at multiple levels of detail; and finally, we evaluate the impact of various algorithm choices on our output rigs.1

RigNet: neural rigging for articulated characters

We present RigNet, an end-to-end automated method for producing animation rigs from input character models. Given an input 3D model representing an articulated character, RigNet predicts a skeleton that matches the animator expectations in joint placement and topology. It also estimates surface skin weights based on the predicted skeleton. Our method is based on a deep architecture that directly operates on the mesh representation without making assumptions on shape class and structure. The architecture is trained on a large and diverse collection of rigged models, including their mesh, skeletons and corresponding skin weights. Our evaluation is three-fold: we show better results than prior art when quantitatively compared to animator rigs; qualitatively we show that our rigs can be expressively posed and animated at multiple levels of detail; and finally, we evaluate the impact of various algorithm choices on our output rigs.

Chris Landreth

Papers

JALI: an animator-centric viseme model for expressive lip synchronization

Visemenet: audio-driven animator-centric speech animation

RigNet: neural rigging for articulated characters

RigNet: Neural Rigging for Articulated Characters

VisemeNet: Audio-Driven Animator-Centric Speech Animation