A real-time framework for visual feedback of articulatory data using statistical shape models

2016/12/19 by James, Kristy, Hewer, Alexander, Steiner, Ingmar +1
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · doi:10.48550/arxiv.1612.06114

Abstract

We present a novel open-source framework for visualizing electromagnetic articulography (EMA) data in real-time, with a modular framework and anatomically accurate tongue and palate models derived by multilinear subspace learning.

Related

• A statistical shape space model of the palate surface trained on 3D MRI scans of the vocal tract
• Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator
• Deep Speech Synthesis from Articulatory Representations
• The 2D+ Dynamic Articulatory Model DYNARTmo: Tongue-Palate Contact Area Estimation
• Tracking Articulatory Dynamics in Speech with a Fixed-Weight BiLSTM-CNN Architecture