Loading...
Please wait, while we are loading the content...
Similar Documents
Inversion from Audiovisual Speech to Articulatory Information by Exploiting Multimodal Data
| Content Provider | CiteSeerX |
|---|---|
| Author | Maragos, P. Aron, M. Roussos, A. Katsamanis, A. Berger, M. -O. |
| Abstract | We present an inversion framework to identify speech production properties from audiovisual in-formation. Our system is built on a multimodal articulatory dataset comprising ultrasound, X-ray, magnetic resonance images, electromagnetic artic-ulography data as well as audio and stereovisual recordings of the speaker. Visual information is captured via stereovision while the vocal tract state is represented by a properly trained articulatory model. The audiovisual-to-articulation relationship is approximated by an adaptive piecewise linear mapping. The presented system can recover the hid-den vocal tract shapes and may serve as a basis for a more widely applicable inversion setup. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Applicable Inversion Setup Trained Articulatory Model Audiovisual In-formation Audiovisual Speech Hid-den Vocal Tract Shape Articulatory Information Visual Information Magnetic Resonance Image Adaptive Piecewise Linear Mapping Stereovisual Recording Presented System Multimodal Articulatory Dataset Electromagnetic Artic-ulography Data Multimodal Data Speech Production Property Inversion Framework Vocal Tract State Audiovisual-to-articulation Relationship |
| Content Type | Text |
