20.500.12556/DKUM-95219 Controllable speech-driven gesture generation with selective activation of weakly supervised controls Generating realistic and contextually appropriate gestures is crucial for creating engaging embodied conversational agents. Although speech is the primary input for gesture generation, adding controls like gesture velocity, hand height, and emotion is essential for generating more natural, human-like gestures. However, current approaches to controllable gesture generation often utilize a limited number of control parameters and lack the ability to activate/deactivate them selectively. Therefore, in this work, we propose the Cont-Gest model, a Transformer-based gesture generation model that enables selective control activation through masked training and a control fusion strategy. Furthermore, to better support the development of such models, we propose a novel evaluation-driven development (EDD) workflow, which combines several iterative tasks: automatic control signal extraction, control specification, visual (subjective) feedback, and objective evaluation. This workflow enables continuous monitoring of model performance and facilitates iterative refinement through feedback-driven development cycles. For objective evaluation, we are using the validated Kinetic–Hellinger distance, an objective metric that correlates strongly with the human perception of gesture quality. We evaluated multiple model configurations and control dynamics strategies within the proposed workflow. Experimental results show that Feature-wise Linear Modulation (FiLM) conditioning, combined with single-mask training and voice activity scaling, achieves the best balance between gesture quality and adherence to control inputs. gesture generation objective evaluation selective control activation transformers weakly supervised learning ustvarjanje gest objektivno vrednotenje transfromatorji slabo nadzorovano učenje true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/applsci © 2025 by the authors Članek v reviji 2025-09-09 10:40:49 2025-09-09 10:40:49 2025-09-10 03:37:02 0000-00-00 00:00:00 2025 0 0 21 str. iss. 17, [article no.] 9467 Vol. 15 2025 0000-00-00 Zaloznikova Objavljeno apc 2025-08-10 2025-08-26 2025-08-28 004.8 248164099 10.3390/app15179467 2076-3417 applsci-15-09467-v2.pdf applsci-15-09467-v2.pdf 1 C4928D336842855F4B0DD151617041C0 edad65524bfbd71ded923107ee0082b96e0ebc6c23f9b052b3a520e9c273da40 4eb7eb40-8d59-11f0-9299-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=197977 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0