Design of a Multimodal Input Interface for a Dialogue System

Neto, João Paulo; Cassaca, Renato; Viveiros, Márcio; Mourão, Márcio

doi:10.1007/11751984_18

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to [3], the relation between European Portuguese phones and their visual representation can be modeled with 15 correspondences. Using this information, the phone to viseme mapping is processed using a table.…”

Section: B Visemesmentioning

confidence: 99%

See 1 more Smart Citation

Talking avatar for web-based interfaces

Nunes

Sá

Perdigão

2011

2011 IEEE EUROCON - International Conference on Computer as a Tool

View full text Add to dashboard Cite

In this paper we present an approach for creating interactive and speaking avatar models, based on standard face images. We have started from a 3D human face model that can be adjusted to a particular face. In order to adjust the 3D model from a 2D image, a new method with 2 steps is presented. First, a process based on Procrustes analysis is applied in order to find the best match for input key points, obtaining the rotation, translation and scale needed to best fit the model to the photo. Then, using the resulting model we refine the face mesh by applying a linear transform on each vertex. In terms of visual speech animation, we have considered a total of 15 different positions to accurately model the articulation of Portuguese language -the visemes. For normalization purposes, each viseme is defined from the generic neutral face. The animation process is visually represented with linear time interpolation, given a sequence of visemes and its instants of occurrence.

show abstract

Section: B Visemesmentioning

confidence: 99%

“…Although there are several approaches concerning model presentation, i.e. [1,3] and model deformation, [4,5,6], this work presents a new approach for avatar creation, which is achieved only with a photo with no special requirements and no previous learning.…”

Section: Introductionmentioning

confidence: 99%

Talking avatar for web-based interfaces

Nunes

Sá

Perdigão

2011

2011 IEEE EUROCON - International Conference on Computer as a Tool

View full text Add to dashboard Cite

show abstract

“…Furthermore, we have a Question & Answer module (Neto, Cassaca, Viveiros, Mourao, 2006) functioning as a domain knowledge datacenter. Stored here is every question and possible answer in agent's sphere of expertise.…”

Section: An Innovative Hci Systemmentioning

confidence: 99%

Immersive Cultural Experience through Innovative Multimedia Applications: The History of Monserrate Palace in Sintra (Portugal) Presented by Virtual Agents

Neto

2012

International Journal of Heritage in the Digital Era

View full text Add to dashboard Cite

ABSTRACT:We are currently in the process of making a series of interconnected multimedia applications, in order to value and enliven the monuments of Sintra, Portugal -classified by Unesco as World Heritage site in 1995. This national project, Fala Comigo (Talk2Me), aspires to present new contents, not only to scholars but also to an unlimited number of visitors, and thus achieve a social, cultural, educational and civic mission. As an interdisciplinary project, the historians generate the content, while the engineers and technicians design content-driven multimedia applications. In this phase, our case study is the Monserrate Palace, a revivalist building of the 19 th century. These applications profoundly rely on a balance between renewed heritage contents, a rigorous scientific approach and stunning designs. We encounter innovative multimodal ways of visitor-application interaction, mainly with the addition of virtual agents that works as guide assistants with educational purposes.

show abstract