Youngwoo Yoon

Rajmund Nagy, Hendric Voss, Thanh Hoang-Minh et al.

We review human evaluation practices in automated, speech-driven 3D gesture generation and find a lack of standardisation and frequent use of flawed experimental setups. This leads to a situation where it is impossible to know how different methods compare, or what the state of the art is. In order to address common shortcomings of evaluation design, and to standardise future user studies in gesture-generation works, we introduce a detailed human evaluation protocol for the widely-used BEAT2 motion-capture dataset. Using this protocol, we conduct large-scale crowdsourced evaluation to rank six recent gesture-generation models -- each trained by its original authors -- across two key evaluation dimensions: motion realism and speech-gesture alignment. Our results provide strong evidence that 1) newer models do not consistently outperform earlier approaches; 2) published claims of high motion realism or speech-gesture alignment may not hold up under rigorous evaluation; and 3) the field must adopt disentangled assessments of motion quality and multimodal alignment for accurate benchmarking in order to make progress. Finally, in order to drive standardisation and enable new evaluation research, we will release five hours of synthetic motion from the benchmarked models; over 750 rendered video stimuli from the user studies -- enabling new evaluations without model reimplementation required -- alongside our open-source rendering script, and the 16,000 pairwise human preference votes collected for our benchmark.

Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko et al.

This paper reports on the second GENEA Challenge to benchmark data-driven automatic co-speech gesture generation. Participating teams used the same speech and motion dataset to build gesture-generation systems. Motion generated by all these systems was rendered to video using a standardised visualisation pipeline and evaluated in several large, crowdsourced user studies. Unlike when comparing different research papers, differences in results are here only due to differences between methods, enabling direct comparison between systems. This year's dataset was based on 18 hours of full-body motion capture, including fingers, of different persons engaging in dyadic conversation. Ten teams participated in the challenge across two tiers: full-body and upper-body gesticulation. For each tier we evaluated both the human-likeness of the gesture motion and its appropriateness for the specific speech signal. Our evaluations decouple human-likeness from gesture appropriateness, which previously was a major challenge in the field. The evaluation results are a revolution, and a revelation. Some synthetic conditions are rated as significantly more human-like than human motion capture. To the best of our knowledge, this has never been shown before on a high-fidelity avatar. On the other hand, all synthetic motion is found to be vastly less appropriate for the speech than the original motion-capture recordings. Additional material is available via the project website at https://youngwoo-yoon.github.io/GENEAchallenge2022/

Taras Kucherenko, Rajmund Nagy, Youngwoo Yoon et al.

This paper reports on the GENEA Challenge 2023, in which participating teams built speech-driven gesture-generation systems using the same speech and motion dataset, followed by a joint evaluation. This year's challenge provided data on both sides of a dyadic interaction, allowing teams to generate full-body motion for an agent given its speech (text and audio) and the speech and motion of the interlocutor. We evaluated 12 submissions and 2 baselines together with held-out motion-capture data in several large-scale user studies. The studies focused on three aspects: 1) the human-likeness of the motion, 2) the appropriateness of the motion for the agent's own speech whilst controlling for the human-likeness of the motion, and 3) the appropriateness of the motion for the behaviour of the interlocutor in the interaction, using a setup that controls for both the human-likeness of the motion and the agent's own speech. We found a large span in human-likeness between challenge submissions, with a few systems rated close to human mocap. Appropriateness seems far from being solved, with most submissions performing in a narrow range slightly above chance, far behind natural motion. The effect of the interlocutor is even more subtle, with submitted systems at best performing barely above chance. Interestingly, a dyadic system being highly appropriate for agent speech does not necessarily imply high appropriateness for the interlocutor. Additional material is available via the project website at https://svito-zar.github.io/GENEAchallenge2023/ .

Taras Kucherenko, Pieter Wolfert, Youngwoo Yoon et al.

This paper reports on the second GENEA Challenge to benchmark data-driven automatic co-speech gesture generation. Participating teams used the same speech and motion dataset to build gesture-generation systems. Motion generated by all these systems was rendered to video using a standardised visualisation pipeline and evaluated in several large, crowdsourced user studies. Unlike when comparing different research papers, differences in results are here only due to differences between methods, enabling direct comparison between systems. The dataset was based on 18 hours of full-body motion capture, including fingers, of different persons engaging in a dyadic conversation. Ten teams participated in the challenge across two tiers: full-body and upper-body gesticulation. For each tier, we evaluated both the human-likeness of the gesture motion and its appropriateness for the specific speech signal. Our evaluations decouple human-likeness from gesture appropriateness, which has been a difficult problem in the field. The evaluation results show some synthetic gesture conditions being rated as significantly more human-like than 3D human motion capture. To the best of our knowledge, this has not been demonstrated before. On the other hand, all synthetic motion is found to be vastly less appropriate for the speech than the original motion-capture recordings. We also find that conventional objective metrics do not correlate well with subjective human-likeness ratings in this large evaluation. The one exception is the Fréchet gesture distance (FGD), which achieves a Kendall's tau rank correlation of around $-0.5$. Based on the challenge results we formulate numerous recommendations for system building and evaluation.

Antoine Maiorca, Youngwoo Yoon, Thierry Dutoit

Evaluating the Quality of a Synthesized Motion with the Fréchet Motion Distance

Shuhong Lu, Youngwoo Yoon, Andrew Feng

Synthesizing realistic co-speech gestures is an important and yet unsolved problem for creating believable motions that can drive a humanoid robot to interact and communicate with human users. Such capability will improve the impressions of the robots by human users and will find applications in education, training, and medical services. One challenge in learning the co-speech gesture model is that there may be multiple viable gesture motions for the same speech utterance. The deterministic regression methods can not resolve the conflicting samples and may produce over-smoothed or damped motions. We proposed a two-stage model to address this uncertainty issue in gesture synthesis by modeling the gesture segments as discrete latent codes. Our method utilizes RQ-VAE in the first stage to learn a discrete codebook consisting of gesture tokens from training data. In the second stage, a two-level autoregressive transformer model is used to learn the prior distribution of residual codes conditioned on input speech context. Since the inference is formulated as token sampling, multiple gesture sequences could be generated given the same speech input using top-k sampling. The quantitative results and the user study showed the proposed method outperforms the previous methods and is able to generate realistic and diverse gesture motions.

Eui Jun Hwang, Sukmin Cho, Huije Lee et al.

This work addresses the challenges associated with the use of glosses in both Sign Language Translation (SLT) and Sign Language Production (SLP). While glosses have long been used as a bridge between sign language and spoken language, they come with two major limitations that impede the advancement of sign language systems. First, annotating the glosses is a labor-intensive and time-consuming process, which limits the scalability of datasets. Second, the glosses oversimplify sign language by stripping away its spatio-temporal dynamics, reducing complex signs to basic labels and missing the subtle movements essential for precise interpretation. To address these limitations, we introduce Universal Gloss-level Representation (UniGloR), a framework designed to capture the spatio-temporal features inherent in sign language, providing a more dynamic and detailed alternative to the use of the glosses. The core idea of UniGloR is simple yet effective: We derive dense spatio-temporal representations from sign keypoint sequences using self-supervised learning and seamlessly integrate them into SLT and SLP tasks. Our experiments in a keypoint-based setting demonstrate that UniGloR either outperforms or matches the performance of previous SLT and SLP methods on two widely-used datasets: PHOENIX14T and How2Sign.

Youngwoo Yoon, Keunwoo Park, Minsu Jang et al.

Non-verbal behavior is essential for embodied agents like social robots, virtual avatars, and digital humans. Existing behavior authoring approaches including keyframe animation and motion capture are too expensive to use when there are numerous utterances requiring gestures. Automatic generation methods show promising results, but their output quality is not satisfactory yet, and it is hard to modify outputs as a gesture designer wants. We introduce a new gesture generation toolkit, named SGToolkit, which gives a higher quality output than automatic methods and is more efficient than manual authoring. For the toolkit, we propose a neural generative model that synthesizes gestures from speech and accommodates fine-level pose controls and coarse-level style controls from users. The user study with 24 participants showed that the toolkit is favorable over manual authoring, and the generated gestures were also human-like and appropriate to input speech. The SGToolkit is platform agnostic, and the code is available at https://github.com/ai4r/SGToolkit.

Youngwoo Yoon, Bok Cha, Joo-Haeng Lee et al.

For human-like agents, including virtual avatars and social robots, making proper gestures while speaking is crucial in human--agent interaction. Co-speech gestures enhance interaction experiences and make the agents look alive. However, it is difficult to generate human-like gestures due to the lack of understanding of how people gesture. Data-driven approaches attempt to learn gesticulation skills from human demonstrations, but the ambiguous and individual nature of gestures hinders learning. In this paper, we present an automatic gesture generation model that uses the multimodal context of speech text, audio, and speaker identity to reliably generate gestures. By incorporating a multimodal context and an adversarial training scheme, the proposed model outputs gestures that are human-like and that match with speech content and rhythm. We also introduce a new quantitative evaluation metric for gesture generation models. Experiments with the introduced metric and subjective human evaluation showed that the proposed gesture generation model is better than existing end-to-end generation models. We further confirm that our model is able to work with synthesized audio in a scenario where contexts are constrained, and show that different gesture styles can be generated for the same speech by specifying different speaker identities in the style embedding space that is learned from videos of various speakers. All the code and data is available at https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context.

Jae-Woo Choi, Hyungmin Kim, Hyobin Ong et al.

Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods still struggle with complex, long-horizon tasks because they rely on a monolithic trajectory that entangles all past decisions and observations, attempting to solve the entire task in a single unified process. To address this limitation, we propose ReAcTree, a hierarchical task-planning method that decomposes a complex goal into more manageable subgoals within a dynamically constructed agent tree. Each subgoal is handled by an LLM agent node capable of reasoning, acting, and further expanding the tree, while control flow nodes coordinate the execution strategies of agent nodes. In addition, we integrate two complementary memory systems: each agent node retrieves goal-specific, subgoal-level examples from episodic memory and shares environment-specific observations through working memory. Experiments on the WAH-NL and ALFRED datasets demonstrate that ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse LLMs. Notably, on WAH-NL, ReAcTree achieves a 61% goal success rate with Qwen 2.5 72B, nearly doubling ReAct's 31%.

Jae-Woo Choi, Youngwoo Yoon, Hyobin Ong et al.

Large language models (LLMs) have recently received considerable attention as alternative solutions for task planning. However, comparing the performance of language-oriented task planners becomes difficult, and there exists a dearth of detailed exploration regarding the effects of various factors such as pre-trained model selection and prompt construction. To address this, we propose a benchmark system for automatically quantifying performance of task planning for home-service embodied agents. Task planners are tested on two pairs of datasets and simulators: 1) ALFRED and AI2-THOR, 2) an extension of Watch-And-Help and VirtualHome. Using the proposed benchmark system, we perform extensive experiments with LLMs and prompts, and explore several enhancements of the baseline planner. We expect that the proposed benchmark tool would accelerate the development of language-oriented task planners.

Jiyu Lim, Youngwoo Yoon, Kwanghyun Park

Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study proposes CRISP (Critique-and-Replan for Interactive Social Presence), an autonomous framework where a robot critiques and replans its own actions by leveraging a Vision-Language Model (VLM) as a `human-like social critic.' CRISP integrates (1) extraction of movable joints and constraints by analyzing the robot's description file (e.g., MJCF), (2) generation of step-by-step behavior plans based on situational context, (3) generation of low-level joint control code by referencing visual information (joint range-of-motion visualizations), (4) VLM-based evaluation of social appropriateness and naturalness, including pinpointing erroneous steps, and (5) iterative refinement of behaviors through reward-based search. This approach is not tied to a specific robot API; it can generate subtly different, human-like motions on various platforms using only the robot's structure file. In a user study involving five different robot types and 20 scenarios, including mobile manipulators and humanoids, our proposed method achieved significantly higher preference and situational appropriateness ratings compared to previous methods. This research presents a general framework that minimizes human intervention while expanding the robot's autonomous interaction capabilities and cross-platform applicability. Detailed result videos and supplementary information regarding this work are available at: https://limjiyu99.github.io/inner-critic/

Taewoo Kim, Youngwoo Yoon, Jaehong Kim

Robotic catching has traditionally focused on single-handed systems, which are limited in their ability to handle larger or more complex objects. In contrast, bimanual catching offers significant potential for improved dexterity and object handling but introduces new challenges in coordination and control. In this paper, we propose a novel framework for learning dexterous bimanual catching skills using Heterogeneous-Agent Reinforcement Learning (HARL). Our approach introduces an adversarial reward scheme, where a throw agent increases the difficulty of throws-adjusting speed-while a catch agent learns to coordinate both hands to catch objects under these evolving conditions. We evaluate the framework in simulated environments using 15 different objects, demonstrating robustness and versatility in handling diverse objects. Our method achieved approximately a 2x increase in catching reward compared to single-agent baselines across 15 diverse objects.

Taras Kucherenko, Patrik Jonell, Youngwoo Yoon et al.

Co-speech gestures, gestures that accompany speech, play an important role in human communication. Automatic co-speech gesture generation is thus a key enabling technology for embodied conversational agents (ECAs), since humans expect ECAs to be capable of multi-modal communication. Research into gesture generation is rapidly gravitating towards data-driven methods. Unfortunately, individual research efforts in the field are difficult to compare: there are no established benchmarks, and each study tends to use its own dataset, motion visualisation, and evaluation methodology. To address this situation, we launched the GENEA Challenge, a gesture-generation challenge wherein participating teams built automatic gesture-generation systems on a common dataset, and the resulting systems were evaluated in parallel in a large, crowdsourced user study using the same motion-rendering pipeline. Since differences in evaluation outcomes between systems now are solely attributable to differences between the motion-generation methods, this enables benchmarking recent approaches against one another in order to get a better impression of the state of the art in the field. This paper reports on the purpose, design, results, and implications of our challenge.

Patrik Jonell, Youngwoo Yoon, Pieter Wolfert et al.

In many research areas, for example motion and gesture generation, objective measures alone do not provide an accurate impression of key stimulus traits such as perceived quality or appropriateness. The gold standard is instead to evaluate these aspects through user studies, especially subjective evaluations of video stimuli. Common evaluation paradigms either present individual stimuli to be scored on Likert-type scales, or ask users to compare and rate videos in a pairwise fashion. However, the time and resources required for such evaluations scale poorly as the number of conditions to be compared increases. Building on standards used for evaluating the quality of multimedia codecs, this paper instead introduces a framework for granular rating of multiple comparable videos in parallel. This methodology essentially analyses all condition pairs at once. Our contributions are 1) a proposed framework, called HEMVIP, for parallel and granular evaluation of multiple video stimuli and 2) a validation study confirming that results obtained using the tool are in close agreement with results of prior studies using conventional multiple pairwise comparisons.

Youngwoo Yoon, Woo-Ri Ko, Minsu Jang et al.

Co-speech gestures enhance interaction experiences between humans as well as between humans and robots. Existing robots use rule-based speech-gesture association, but this requires human labor and prior knowledge of experts to be implemented. We present a learning-based co-speech gesture generation that is learned from 52 h of TED talks. The proposed end-to-end neural network model consists of an encoder for speech text understanding and a decoder to generate a sequence of gestures. The model successfully produces various gestures including iconic, metaphoric, deictic, and beat gestures. In a subjective evaluation, participants reported that the gestures were human-like and matched the speech content. We also demonstrate a co-speech gesture with a NAO robot working in real time.