INESC-ID

About: INESC-ID is a nonprofit organization based out in Lisbon, Portugal. It is known for research contribution in the topics: Computer science & Context (language use). The organization has 932 authors who have published 2618 publications receiving 37658 citations.

Synthesizing robotic handwriting motion by learning from human demonstrations

Abstract: This paper contributes a novel framework that enables a robotic agent to efficiently learn and synthesize believable handwriting motion. We situate the framework as a foundation with the goal of allowing children to observe, correct and engage with the robot to learn themselves the handwriting skill. The framework adapts the principle behind ensemble methods - where improved performance is obtained by combining the output of multiple simple algorithms - in an inverse optimal control problem. This integration addresses the challenges of rapid extraction and representation of multiple-mode motion trajectories, with the cost forms which are transferable and interpretable in the development of the robot compliance control. It also introduces the incorporation of a human movement inspired feature, which provides intuitive motion modulation to generalize the synthesis with poor robotic written samples for children to identify and correct. We present the results on the success of synthesizing a variety of natural-looking motion samples based upon the learned cost functions. The framework is validated by a user study, where the synthesized dynamical motion is shown to be hard to distinguish from the real human handwriting.

A new look at the fractionalization of the logistic equation

Abstract: The fractional version of the logistic equation will be studied in this paper. Motivated by unsuccessful previous papers, we showed how to obtain the correct solution. The algorithm is very simple. Its numerical implementation will be studied and exemplified using a Pade approximation.

Incorporating acoustical modelling of phone transitions in an hybrid ANN/HMM speech recognizer

Abstract: Speech recognition based on connectionist approaches is one of the most successful alternatives to widespread Gaussian systems. One of the main claims against hybrid recognizers is the increased complexity for context-dependent phone modelling, which is a key aspect in medium to large size vocabulary tasks. In this paper, a baseline hybrid system based on monophone recognition units is improved by incorporating acoustical modelling of phone transitions. First, a single state monophone model is extended to multiple state sub-phoneme modelling. Then, a reduced set of diphone recognition units is incorporated to model phone transitions. The proposed approach shows a 26.8% and 23.8% relative word error rate reduction compared to baseline hybrid system in two selected WSJ evaluation test sets. Additionally, improved performance compared to a reference Gaussian system based on word-internal context-dependent triphones and comparable results to cross-word triphone system are reported. Index Terms: speech recognition, context modelling, connectionist system

A Controlled Natural Language Approach for Integrating Requirements and Model-Driven Engineering

Abstract: Despite the efforts made during the last decades, Software Engineering still presents several issues concerning software products' quality. Requirements Engineering plays a important role regarding software quality, since it deals with the clear definition of the target system's scope. Moreover, Requirements Engineering is crucial to deal with change management, which is required to ensure that the final product reflects the stakeholders' expectations, namely the client and end-users business-related needs. We advocate the need to address the open issues regarding the requirements development process, namely to mitigate the drawbacks of using informal natural language, such as ambiguity and inconsistency. Moreover, we recognize the importance of automation to enhance productivity by avoiding repetitive and error-prone activities. In this paper, we propose a new socio-technical approach to overcome these software quality problems, consisting on the deep integration of Requirements Engineering with Model-Driven Engineering processes. This approach is based upon a controlled natural language for requirements specification, supporting the automatic extraction and verification of requirements models with Natural Language Processing techniques. The current results consist on the development of a Wiki-based tool prototype to validate our research ideas.