Samuel Silva — PhD — IEETA, University of Aveiro

My goal is to foster a better understanding of phenomena by a transversal approach considering contributions from data acquisition, processing and analysis methods up to multimodal interactive visualization leveraging user insights.

Research in Psychology

Continuous Flash Suppression

Research in Psychology

Low road

Quantitative Articulatory Analysis

RT-MRI sequences

Quantitative Articulatory Analysis

To move towards a more objective assessment of articulatory differences, between and along sounds, an abstract representation of the differences found for notable anatomical regions/articulators is proposed. The differences are computed using normalized quantitative measures.

Project: HERON II

Vocal Tract Segmentation

RT-MRI Sequences

Vocal Tract Segmentation

Under Construction!

Project: HERON II

LV Functional Analysis

Coronary CT Angiography

LV Functional Analysis

Under construction.

Project: N/A

PolyMeCo

Polygonal Mesh Analysis and Comparison

Tool for analysing and comparing polygonal mesh models.

Project: N/A

Resources related with research work in which I collaborate.

Detecting Nasal Vowels in Speech Interfaces based on Surface Electromyography

by João Freitas, António Teixeira, Samuel Silva, Catarina Oliveira and Miguel Sales Dias

Summary:

Nasality is a very important characteristic of several languages, such as European Portuguese. This paper addresses the challenge of nasality detection in surface electromyography (EMG) based speech interfaces. We explore the existence of useful information about the velum movement and also assess if deeper muscles can be sensed using surface electrodes in the regions of the face and neck and the best electrode location to do so. The applied procedure uses Real-Time Magnetic Resonance Imaging (RT-MRI), collected from the same speakers, providing a method to interpret EMG data. Bellow, the datasets corresponding to the EMG signals and the velum aperture curves, extracted for RT-MRI sequences, are provided. This work is currently under consideration for publication in a journal and additional details will be provided as soon as possible or upon request.

Datasets:

sEMG data, velum aperture curves (from RT-MRI)