Abstract
We propose a visual parametrization method for the task of lipreading and audiovisual speech recognition from frontal face videos. The presented features utilize learned spatiotemporal convolutions in a deep neural network that is trained to predict phonemes on a frame level. The network is trained on a manually transcribed moderate size dataset of Czech television broadcast, but we show that the resulting features generalize well to other languages as well. On a publicly available OuluVS dataset, a result of 91% word accuracy was achieved using vanilla convolutional features, and 97.2% after fine tuning – substantial state of the art improvements in this popular benchmark. Contrary to most of the work on lipreading, we also demonstrate usefulness of the proposed parametrization in the task of continuous audiovisual speech recognition.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: LipNet: sentence-level lipreading. CoRR abs/1611.01599 (2016). http://arxiv.org/abs/1611.01599
Chung, J.S., Senior, A.W., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. CoRR abs/1611.05358 (2016). http://arxiv.org/abs/1611.05358
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, pp. 1725–1732. IEEE Computer Society, Washington, DC (2014)
Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23–28 June 2014, pp. 1867–1874 (2014)
King, D.E.: Dlib-ml: a machine learning toolkit. J. Mach. Learn. Res. 10, 1755–1758 (2009)
Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, 28 June–2 July 2011, pp. 689–696 (2011)
Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H., Ogata, T.: Lipreading using convolutional neural network. In: International Speech and Communication Association, pp. 1149–1153 (2014)
Nouza, J., Psutka, J., Uhlíř, J.: Phonetic alphabet for speech recognition of Czech (1997)
Palecek, K.: Lipreading using spatiotemporal histogram of oriented gradients. In: EUSIPCO 2016, Budapest, Hungary, pp. 1882–1885 (2016)
Pei, Y., Kim, T., Zha, H.: Unsupervised random forest manifold alignment for lipreading. In: IEEE International Conference on Computer Vision, Sydney, Australia, pp. 129–136 (2013)
Ramage, M.D.: Disproving visemes as the basic visual unit of speech (2013). http://www.mramage.id.au/phd
Wand, M., Koutník, J., Schmidhuber, J.: Lipreading with long short-term memory. CoRR abs/1601.08188 (2016). http://arxiv.org/abs/1601.08188
Zhao, G., Barnard, M., Pietikäinen, M.: Lipreading with local spatiotemporal descriptors. IEEE Trans. Multimedia 11(7), 1254–1265 (2009)
Zhou, Z., Zhao, G., Hong, X., Pietikinen, M.: A review of recent advances in visual speech decoding. Image Vision Comput. 32(9), 590–605 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Paleček, K. (2017). Spatiotemporal Convolutional Features for Lipreading. In: Ekštein, K., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2017. Lecture Notes in Computer Science(), vol 10415. Springer, Cham. https://doi.org/10.1007/978-3-319-64206-2_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-64206-2_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64205-5
Online ISBN: 978-3-319-64206-2
eBook Packages: Computer ScienceComputer Science (R0)