University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Learning the mapping function from voltage amplitudes to sensor positions in 3D-EMA using deep neural networks

Kroos, Christian and Plumbley, Mark (2017) Learning the mapping function from voltage amplitudes to sensor positions in 3D-EMA using deep neural networks In: Interspeech 2017, 20 - 24 August 2017, Stockholm, Sweden.

[img]
Preview
Text
kroos_plumbley_Interspeech2017_revised.pdf - Accepted version Manuscript

Download (1MB) | Preview

Abstract

The first generation of three-dimensional Electromagnetic Articulography devices (Carstens AG500) suffered from occasional critical tracking failures. Although now superseded by new devices, the AG500 is still in use in many speech labs and many valuable data sets exist. In this study we investigate whether deep neural networks (DNNs) can learn the mapping function from raw voltage amplitudes to sensor positions based on a comprehensive movement data set. This is compared to arriving sample by sample at individual position values via direct optimisation as used in previous methods. We found that with appropriate hyperparameter settings a DNN was able to approximate the mapping function with good accuracy, leading to a smaller error than the previous methods, but that the DNN-based approach was not able to solve the tracking problem completely.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
NameEmailORCID
Kroos, Christianc.kroos@surrey.ac.ukUNSPECIFIED
Plumbley, Markm.plumbley@surrey.ac.ukUNSPECIFIED
Date : 24 August 2017
Identification Number : 10.21437/Interspeech.2017-1681
Copyright Disclaimer : Copyright 2017 ISCA (the International Speech Communication Association).
Uncontrolled Keywords : Electromagnetic Articulography, 3D-EMA, position estimation, deep neural networks, DNN, speech articulation
Depositing User : Melanie Hughes
Date Deposited : 02 Jun 2017 10:43
Last Modified : 24 Aug 2017 07:59
URI: http://epubs.surrey.ac.uk/id/eprint/841277

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800