Abstract
Existing work on the animation of signing avatars often relies on pure procedural techniques or on the playback of Motion Capture (MoCap) data. While the first solution results in robotic and unnatural motions, the second one is very limited in the number of signs that it can produce. In this paper, we propose to implement data-driven motion synthesis techniques to increase the variety of Sign Language (SL) motions that can be made from a limited database. In order to generate new signs and inflection mechanisms based on an annotated French Sign Language MoCap corpus, we rely on phonological recombination, i.e. on the motion retrieval and modular reconstruction of SL content at a phonological level with a particular focus on three phonological components of SL: hand placement, hand configuration and hand movement. We propose to modify the values taken by those components in different signs to create their inflected version or completely new signs by (i) applying motion retrieval at a phonological level to exchange the value of one component without any modification, (ii) editing the retrieved data with different operators, or, (iii) using conventional motion generation techniques such as interpolation or inverse kinematics, which are parameterized to comply to the kinematic properties of real motion observed in the data set. The quality of the synthesized motions is perceptually assessed through two distinct evaluations that involved 75 and 53 participants respectively.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
We call channel the set of joints corresponding to a phonological component.
It can also be interesting to add noise to achieve a similar effect.
Not to mention the overall attitude and facial expression that are not part of this work.
One of the 4 remaining ground truth videos was removed from the questionnaire beforehand and was not showed to the participants as it contained an artefact.
We considered a significant difference for a p-value \({< 0.01}\).
A video showing our synthesis results is available at this address: http://sltat.cs.depaul.edu/2019/naert.mp4.
References
Aristidou A, Lasenby J (2011) Fabrik: a fast, iterative solver for the inverse kinematics problem. Graph Models 73(5):243–260
Battison R (1974) Phonological deletion in American sign language. Sign Lang Stud 5(1):1–19
Battison R (1978) Lexical borrowing in American sign language. Linstok Press, Silver Spring, MD
Boutora L (2006) Vers un inventaire ordonné des configurations manuelles de la langue des Signes Française. In: Journées d’Études sur la Parole (JEP)
Braffort A, Bolot L, Filhol M, Verrecchia C (2007) Démonstrations d’Elsi, la signeuse virtuelle du LIMSI. In: Conférence sur le Traitement Automatique des Langues Naturelles (TALN), Traitement automatique des langues des signes (atelier TALS), Toulouse https://hal.archives-ouvertes.fr/hal-02285133
Brock H, Nakadai K (2018) Deep JSLC: a multimodal corpus collection for data-driven generation of Japanese sign language expressions. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)
Brun R, Turki A, Laville A (2016) A 3d application to familiarize children with sign language and assess the potential of avatars and motion capture for learning movement. In: Proceedings of the 3rd International Symposium on Movement and Computing, ACM, p 48
Cox S, Lincoln M, Tryggvason J, Nakisa M, Wells M, Tutt M, Abbott S (2003) The development and evaluation of a speech-to-sign translation system to assist transactions. Int J Hum Comput Interact 16(2):141–161. https://doi.org/10.1207/S15327590IJHC1602_02
Cuxac C (2000) La langue des signes française (LSF) : les voies de l’iconocité (French) [French Sign Language: the iconicity ways]. Faits de langues, Ophrys. https://books.google.fr/books?id=UuS7AAAAIAAJ
Delorme M, Filhol M, Braffort A (2009) Animation generation process for sign language synthesis. In: Advances in Computer-Human Interactions, 2009. ACHI’09. Second International Conferences on, IEEE, pp 386–390
Duarte K, Gibet S (2010) Corpus design for signing avatars. Workshop on representation and processing of sign languages: corpora and sign language technologies. Valetta, Malta, pp 1–3 (hal-00505182)
Filhol M, McDonald JC (2020) The synthesis of complex shape deployments in sign language. In: Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives, European Language Resources Association (ELRA), Marseille, pp 61–68, https://www.aclweb.org/anthology/2020.signlang-1.10
Gibet S, Courty N, Duarte K, Le Naour T (2011) The signcom system for data-driven animation of interactive virtual signers: methodology and evaluation. Trans Interact Intell Syst 1(1):1–23
Heloir A, Kipp M (2010) Real-time animation of interactive agents: specification and realization. Appl Artif Intel 24(6):510–529
Kennaway R (2001) Synthetic animation of deaf signing gestures. In: International Gesture Workshop, Springer, pp 146–157
Klima ES, Bellugi U (1979) The signs of language. Harvard University Press, Cambridge
Lebourque T, Gibet S (1999) A complete system for the specification and the generation of sign language gestures. In: International Gesture Workshop, Springer, pp 227–238
Lombardo V, Nunnari F, Damiano R (2010) A virtual interpreter for the Italian sign language. In: International Conference on Intelligent Virtual Agents, Springer, pp 201–207
Lombardo V, Battaglino C, Damiano R, Nunnari F (2011) An avatar-based interface for the Italian sign language. In: Complex, Intelligent and Software Intensive Systems (CISIS), 2011 International Conference on, IEEE, pp 589–594
McDonald J, Wolfe R, Schnepp J, Hochgesang J, Jamrozik DG, Stumbo M, Berke L, Bialek M, Thomas F (2016a) An automated technique for real-time production of lifelike animations of American sign language. Univers Access Inform Soc 15(4):551–566. https://doi.org/10.1007/s10209-015-0407-2
McDonald J, Wolfe R, Wilbur RB, Moncrief R, Malaia E, Fujimoto S, Baowidan S, Stec J (2016b) A new tool to facilitate prosodic analysis of motion capture data and a data-driven technique for the improvement of avatar motion. In: Proceedings of Language Resources and Evaluation Conference (LREC), pp 153–59
Millet A (2004) La langue des signes française (lsf): une langue iconique et spatiale méconnue. Recherche et pratiques pédagogiques en langues de spécialité Cahiers de l’Apliut 23(2):31–44
Millet A (2019) Grammaire descriptive de la langue des signes française: dynamiques iconiques et linguistique générale. UGA Editions, Grenoble
Naert L, Larboulette C, Gibet S (2020) LSF-ANIMAL: a motion capture corpus in French sign language designed for the animation of signing avatars. In: Language Resources and Evaluation Conference (LREC)
Nunnari F, Filhol M, Heloir A (2018) Animating AZEE descriptions using off-the-shelf IK solvers. In: 8th Workshop on the Representation and Processing of Sign Languages: Involving the Language Community (SignLang 2018), 11th edition of the Language Resources and Evaluation Conference (LREC 2018), pp 7–12
Prillwitz S (1989) HamNoSys: Version 2.0; Hamburg notation system for sign languages: an introductory guide. Signum-Verlag, Berlin
Sallandre M, Cuxac C (2001) Iconicity in sign language: a theoretical and methodological point of view. In: Wachsmuth I, Sowa T (eds) Gesture and Sign Languages in Human-Computer Interaction, International Gesture Workshop, GW 2001, London, April 18-20, 2001, Revised Papers, Springer, Lecture Notes in Computer Science, vol 2298, pp 173–180, https://doi.org/10.1007/3-540-47873-6_18
Sandler W, Lillo-Martin D (2006) Sign language and linguistic universals. Cambridge University Press, Cambridge
Stokoe WC (1960) Sign language structure: an outline of the visual communication systems of the American deaf. Studies in Linguistics, Occasional Papers, p. 8
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Naert, L., Larboulette, C. & Gibet, S. Motion synthesis and editing for the generation of new sign language content. Machine Translation 35, 405–430 (2021). https://doi.org/10.1007/s10590-021-09268-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10590-021-09268-y