Advertisement

Progressive Transformers for End-to-End Sign Language Production

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12356)

Abstract

The goal of automatic Sign Language Production (SLP) is to translate spoken language to a continuous stream of sign language video at a level comparable to a human translator. If this was achievable, then it would revolutionise Deaf hearing communications. Previous work on predominantly isolated SLP has shown the need for architectures that are better suited to the continuous domain of full sign sequences.

In this paper, we propose Progressive Transformers, the first SLP model to translate from discrete spoken language sentences to continuous 3D sign pose sequences in an end-to-end manner. A novel counter decoding technique is introduced, that enables continuous sequence generation at training and inference. We present two model configurations, an end-to-end network that produces sign direct from text and a stacked network that utilises a gloss intermediary. We also provide several data augmentation processes to overcome the problem of drift and drastically improve the performance of SLP models.

We propose a back translation evaluation mechanism for SLP, presenting benchmark quantitative results on the challenging RWTH-PHOENIXWeather-2014T (PHOENIX14T) dataset and setting baselines for future research. Code available at https://github.com/BenSaunders27/ProgressiveTransformersSLP.

Keywords

Sign language production Continuous sequence synthesis Transformers Sequence-to-sequence Human pose generation 

Notes

Acknowledgements

This work received funding from the SNSF Sinergia project ‘SMILE’ (CRSII2 160811), the European Union’s Horizon2020 research and innovation programme under grant agreement no. 762021 ‘Content4All’ and the EPSRC project ‘ExTOL’ (EP/R03298X/1). This work reflects only the authors view and the Commission is not responsible for any use that may be made of the information it contains. We would also like to thank NVIDIA Corporation for their GPU grant.

Supplementary material

Supplementary material 1 (mp4 8415 KB)

504452_1_En_40_MOESM2_ESM.pdf (11.3 mb)
Supplementary material 2 (pdf 11600 KB)

References

  1. 1.
    Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2Action: generative adversarial synthesis from Language to action. In: International Conference on Robotics and Automation (ICRA) (2018)Google Scholar
  2. 2.
    Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer Normalization. arXiv preprint arXiv:1607.06450 (2016)
  3. 3.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 (2014)
  4. 4.
    Bauer, B., Hienz, H., Kraiss, K.F.: Video-based continuous sign language recognition using statistical methods. In: Proceedings of 15th International Conference on Pattern Recognition (ICPR) (2000)Google Scholar
  5. 5.
    Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: AAA1 Workshop on Knowledge Discovery in Databases (KDD) (1994)Google Scholar
  6. 6.
    Camgoz, N.C., Hadfield, S., Koller, O., Bowden, R.: SubUNets: end-to-end hand shape and continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  7. 7.
    Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  8. 8.
    Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: joint end-to-end sign language recognition and translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)Google Scholar
  9. 9.
    Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  10. 10.
    Cho, K., van Merriënboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Proceedings of the Syntax, Semantics and Structure in Statistical Translation (SSST) (2014)Google Scholar
  11. 11.
    Cooper, H., Ong, E.J., Pugeault, N., Bowden, R.: Sign Language Recognition using Sub-units. J. Mach. Learn. Res. (JMLR) 13, 2205–2231 (2012)Google Scholar
  12. 12.
    Cui, R., Liu, H., Zhang, C.: Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  13. 13.
    Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: International Conference on Learning Representations (ICLR) (2019)Google Scholar
  14. 14.
    Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (ACL) (2018)Google Scholar
  15. 15.
    Duarte, A.C.: Cross-modal neural sign language translation. In: Proceedings of the ACM International Conference on Multimedia (ICME) (2019)Google Scholar
  16. 16.
    Ebling, S., et al.: SMILE: swiss German sign language dataset. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC) (2018)Google Scholar
  17. 17.
    Forster, J., Schmidt, C., Koller, O., Bellgardt, M., Ney, H.: Extensions of the sign language recognition and translation corpus RWTH-PHOENIX-weather. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC) (2014)Google Scholar
  18. 18.
    Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  19. 19.
    Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  20. 20.
    Glauert, J., Elliott, R., Cox, S., Tryggvason, J., Sheard, M.: VANESSA: a system for communication between deaf and hearing people. Technology and Disability (2006)Google Scholar
  21. 21.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS) (2010)Google Scholar
  22. 22.
    Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)
  23. 23.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  24. 24.
    Huang, C.Z.A., et al.: Music transformer. In: International Conference on Learning Representations (ICLR) (2018)Google Scholar
  25. 25.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  26. 26.
    Kalchbrenner, N., Blunsom, P.: Recurrent continuous translation models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2013)Google Scholar
  27. 27.
    Karpouzis, K., Caridakis, G., Fotinea, S.E., Efthimiou, E.: Educational resources and implementation of a Greek sign language synthesis architecture. Comput. Educ. 49(1), 54–74 (2007)CrossRefGoogle Scholar
  28. 28.
    Kayahan, D., Güngör, T.: A hybrid translation system from Turkish spoken language to Turkish sign language. In: IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) (2019)Google Scholar
  29. 29.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2014)Google Scholar
  30. 30.
    Kipp, M., Heloir, A., Nguyen, Q.: Sign language avatars: animation and comprehensibility. In: International Workshop on Intelligent Virtual Agents (IVA) (2011)Google Scholar
  31. 31.
    Ko, S.K., Kim, C.J., Jung, H., Cho, C.: Neural sign language translation based on human keypoint estimation. Appl. Sci. 9(13), 2683 (2019)CrossRefGoogle Scholar
  32. 32.
    Koller, O., Camgoz, N.C., Bowden, R., Ney, H.: Weakly supervised learning with multi-stream CNN-LSTM-HMMs to discover sequential parallelism in sign language videos. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2019)Google Scholar
  33. 33.
    Koller, O., Forster, J., Ney, H.: Continuous sign language recognition: towards large vocabulary statistical recognition systems handling multiple signers. Computer Vision and Image Understanding (CVIU) (2015)Google Scholar
  34. 34.
    Koller, O., Ney, H., Bowden, R.: Deep hand: how to train a cnn on 1 million hand images when your data is continuous and weakly labelled. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  35. 35.
    Koller, O., Zargaran, S., Ney, H.: Re-sign: re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  36. 36.
    Koller, O., Zargaran, S., Ney, H., Bowden, R.: Deep sign: hybrid CNN-HMM for continuous sign language recognition. In: Proceedings of the British Machine Vision Conference (BMVC) (2016)Google Scholar
  37. 37.
    Kouremenos, D., Ntalianis, K.S., Siolas, G., Stafylopatis, A.: Statistical machine translation for Greek to Greek sign language using parallel corpora produced via rule-based machine translation. In: IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) (2018)Google Scholar
  38. 38.
    Kreutzer, J., Bastings, J., Riezler, S.: Joey NMT: a minimalist NMT toolkit for novices. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2019)Google Scholar
  39. 39.
    Lee, H.Y., et al.: Dancing to music. In: Advances in Neural Information Processing Systems (NIPS) (2019)Google Scholar
  40. 40.
    Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision (CVPR) (2019)Google Scholar
  41. 41.
    Li, N., Liu, S., Liu, Y., Zhao, S., Liu, M.: Neural speech synthesis with transformer network. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)Google Scholar
  42. 42.
    McDonald, J., et al.: Automated technique for real-time production of lifelike animations of American sign language. Universal Access in the Information Society (UAIS) (2016)Google Scholar
  43. 43.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (NIPS) (2013)Google Scholar
  44. 44.
    Mukherjee, S., Ghosh, S., Ghosh, S., Kumar, P., Roy, P.P.: Predicting video-frames using encoder-convlstm combination. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)Google Scholar
  45. 45.
    Orbay, A., Akarun, L.: Neural sign language translation by learning tokenization. arXiv preprint arXiv:2002.00479 (2020)
  46. 46.
    Özdemir, O., Camgöz, N.C., Akarun, L.: Isolated sign language recognition using improved dense trajectories. In: Proceedings of the Signal Processing and Communication Application Conference (SIU) (2016)Google Scholar
  47. 47.
    Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning (ICML) (2018)Google Scholar
  48. 48.
    Paszke, A., et al.: Automatic differentiation in pyTorch. In: NIPS Autodiff Workshop (2017)Google Scholar
  49. 49.
    Plappert, M., Mandery, C., Asfour, T.: Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks. Rob. Auton. Syst. 109, 13–26 (2018)CrossRefGoogle Scholar
  50. 50.
    Ren, Y., et al.: Fastspeech: fast, robust and controllable text to speech. In: Advances in Neural Information Processing Systems (NIPS) (2019)Google Scholar
  51. 51.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (NIPS) (2016)Google Scholar
  52. 52.
    Starner, T., Pentland, A.: Real-time American sign language recognition from video using hidden markov models. In: Shah, M., Jain, R. (eds.) Motion-Based Recognition. Computational Imaging and Vision, vol. 9, pp. 227–243. Springer, Dordrecht (1997).  https://doi.org/10.1007/978-94-015-8935-2_10CrossRefGoogle Scholar
  53. 53.
    Stoll, S., Camgoz, N.C., Hadfield, S., Bowden, R.: Sign language production using neural machine translation and generative adversarial networks. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)Google Scholar
  54. 54.
    Stoll, S., Camgoz, N.C., Hadfield, S., Bowden, R.: Text2Sign: towards sign language production using neural machine translation and generative adversarial networks. International Journal of Computer Vision (IJCV) (2020)Google Scholar
  55. 55.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS) (2014)Google Scholar
  56. 56.
    Süzgün, M., et al.: Hospisign: an interactive sign language platform for hearing impaired. J. Naval Sci. Eng. 11(3), 75–92 (2015)Google Scholar
  57. 57.
    Tamura, S., Kawasaki, S.: Recognition of sign language motion images. Pattern Recogn. 21(4), 343–353 (1988)CrossRefGoogle Scholar
  58. 58.
    Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS) (2017)Google Scholar
  59. 59.
    Vila, L.C., Escolano, C., Fonollosa, J.A., Costa-jussà, M.R.: End-to-end speech translation with the transformer. In: Advances in Speech and Language Technologies for Iberian Languages (IberSPEECH) (2018)Google Scholar
  60. 60.
    Vogler, C., Metaxas, D.: Parallel midden Markov models for American sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (1999)Google Scholar
  61. 61.
    Xiao, Q., Qin, M., Yin, Y.: Skeleton-based Chinese sign language recognition and generation for bidirectional communication between deaf and hearing people. In: Neural Networks (2020)Google Scholar
  62. 62.
    Yin, K.: Sign Language translation with transformers. arXiv preprint arXiv:2004.00588 (2020)
  63. 63.
    Zelinka, J., Kanis, J.: Neural sign language synthesis: words are our glosses. In: The IEEE Winter Conference on Applications of Computer Vision (WACV) (2020)Google Scholar
  64. 64.
    Zelinka, J., Kanis, J., Salajka, P.: NN-based Czech sign language synthesis. In: International Conference on Speech and Computer (SPECOM) (2019)Google Scholar
  65. 65.
    Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: ERNIE: enhanced language representation with informative entities. In: 57th Annual Meeting of the Association for Computational Linguistics (ACL) (2019)Google Scholar
  66. 66.
    Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  67. 67.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of SurreyGuildfordEngland

Personalised recommendations