Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/24710
Appears in Collections:Psychology Book Chapters and Sections
Title: A Data Driven Approach to Audiovisual Speech Mapping
Authors: Abel, Andrew
Marxer, Ricard
Hussain, Amir
Barker, Jon
Watt, Roger
Whitmer, Bill
Derleth, Peter
Contact Email: r.j.watt@stir.ac.uk
Editors: Liu, CL
Hussain, A
Luo, B
Tan, KC
Zeng, Y
Zhang, Z
Citation: Abel A, Marxer R, Hussain A, Barker J, Watt R, Whitmer B & Derleth P (2016) A Data Driven Approach to Audiovisual Speech Mapping In: Liu CL, Hussain A, Luo B, Tan KC, Zeng Y, Zhang Z (ed.) Advances in Brain Inspired Cognitive Systems, Cham, Switzerland: Springer. BICS 2016: International Conference on Brain Inspired Cognitive Systems, 28.11.2016 - 30.11.2016, Beijing, China, pp. 331-342.
Keywords: Audiovisual
Speech processing
Speech mapping
ANNs
Issue Date: Dec-2016
Series/Report no.: Lecture Notes in Computer Science, 10023
Abstract: The concept of using visual information as part of audio speech processing has been of significant recent interest. This paper presents a data driven approach that considers estimating audio speech acoustics using only temporal visual information without considering linguistic features such as phonemes and visemes. Audio (log filterbank) and visual (2D-DCT) features are extracted, and various configurations of MLP and datasets are used to identify optimal results, showing that given a sequence of prior visual frames an equivalent reasonably accurate audio frame estimation can be mapped.
Rights: Publisher policy allows this work to be made available in this repository. Published in Liu CL., Hussain A., Luo B., Tan K., Zeng Y., Zhang Z. (eds) Advances in Brain Inspired Cognitive Systems. BICS 2016. Lecture Notes in Computer Science, vol 10023, published by Springer. The original publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-49685-6_30
URL: http://link.springer.com/chapter/10.1007/978-3-319-49685-6_30
DOI Link: http://dx.doi.org/10.1007/978-3-319-49685-6_30

Files in This Item:
File Description SizeFormat 
abelBics2016Paper-final-submitted.pdf193.3 kBAdobe PDFView/Open



This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.