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

arXiv: https://arxiv.org/abs/2108.00262 · HTML: https://mlsanity.com/paper/2108.00262/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 31 Jul 2021.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [Learning Individual Styles of Conversational Gesture](https://mlsanity.com/paper/1906.04160/) (2019)
- [Video Generation From Text](https://mlsanity.com/paper/1710.00421/) (2017)
- [Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots](https://mlsanity.com/paper/1810.12541/) (2018)
- [Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents](https://mlsanity.com/paper/2101.11101/) (2021)
- [Gesticulator: A framework for semantically-aware speech-driven gesture generation](https://mlsanity.com/paper/2001.09326/) (2020)
- [Analyzing Input and Output Representations for Speech-Driven Gesture Generation](https://mlsanity.com/paper/1903.03369/) (2019)
- [A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020](https://mlsanity.com/paper/2102.11617/) (2021)
- [STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits](https://mlsanity.com/paper/1910.12906/) (2019)
- [Text Guided Person Image Synthesis](https://mlsanity.com/paper/1904.05118/) (2019)
- [Identifying Emotions from Walking using Affective and Deep Features](https://mlsanity.com/paper/1906.11884/) (2019)
- [Speech-driven Animation with Meaningful Behaviors](https://mlsanity.com/paper/1708.01640/) (2017)
- [Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping](https://mlsanity.com/paper/1911.08708/) (2019)
- [Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders](https://mlsanity.com/paper/2009.08906/) (2020)
- [EVA: Generating Emotional Behavior of Virtual Agents using Expressive Features of Gait and Gaze](https://mlsanity.com/paper/1907.02102/) (2019)
- [Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression](https://mlsanity.com/paper/2010.01615/) (2020)

## Built on by (most cited first, 30 of 58)

- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis](https://mlsanity.com/paper/2203.05297/) (2022)
- [GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents](https://mlsanity.com/paper/2303.14613/) (2023)
- [IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions](https://mlsanity.com/paper/2212.07555/) (2022)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [A Comprehensive Review of Data-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2301.05339/) (2023)
- [ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions](https://mlsanity.com/paper/2311.17057/) (2023)
- [DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation](https://mlsanity.com/paper/2401.04747/) (2024)
- [ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis](https://mlsanity.com/paper/2403.17936/) (2024)
- [The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation](https://mlsanity.com/paper/2208.10441/) (2022)
- [QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation](https://mlsanity.com/paper/2305.11094/) (2023)
- [LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation](https://mlsanity.com/paper/2309.09294/) (2023)
- [Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis](https://mlsanity.com/paper/2405.09814/) (2024)
- [Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion](https://mlsanity.com/paper/2312.04466/) (2023)
- [Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings](https://mlsanity.com/paper/2210.01448/) (2022)
- [Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation](https://mlsanity.com/paper/2410.00464/) (2024)
- [Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022](https://mlsanity.com/paper/2303.08737/) (2023)
- [The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings](https://mlsanity.com/paper/2308.12646/) (2023)
- [SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction](https://mlsanity.com/paper/2503.18211/) (2025)
- [BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer](https://mlsanity.com/paper/2310.06851/) (2023)
- [HUMOS: Human Motion Model Conditioned on Body Shape](https://mlsanity.com/paper/2409.03944/) (2024)
- [Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2301.03949/) (2023)
- [ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions](https://mlsanity.com/paper/2305.15748/) (2023)
- [Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation](https://mlsanity.com/paper/2311.17532/) (2023)
- [EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion Model](https://mlsanity.com/paper/2306.11496/) (2023)
- [UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons](https://mlsanity.com/paper/2309.07051/) (2023)
- [Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication](https://mlsanity.com/paper/2403.19467/) (2024)
- [The Effects of Embodiment and Personality Expression on Learning in LLM-based Educational Agents](https://mlsanity.com/paper/2407.10993/) (2024)
- [T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences](https://mlsanity.com/paper/2406.00636/) (2024)

## Abstract (arXiv)

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 two components: a generator to synthesize gestures from a joint embedding space of features encoded from the input speech and the seed poses, and a discriminator to distinguish 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 in both our generator, where it learns affective features from the seed poses to guide the gesture synthesis, and 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 Fr'echet 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.