António J. S. Teixeira

Usability, accessibility and ambient-assisted living: a systematic literature review

Abstract Ambient-assisted living (AAL) is, nowadays, an important research and development area, foreseen as an important instrument to face the demographic aging. The acceptance of the AAL paradigm is closely related to the quality of the available systems, namely in terms of intelligent functions for the user interaction. In that context, usability and accessibility are crucial issues to consider. This paper presents a systematic literature review of AAL technologies, products and services with the objective of establishing the current position regarding user interaction and how are end users involved in the AAL development and evaluation processes. For this purpose, a systematic review of the literature on AAL was undertaken. A total of 1,048 articles were analyzed, 111 of which were mainly related to user interaction and 132 of which described practical AAL systems applied in a specified context and with a well-defined aim. Those articles classified as user interaction and systems were further characterized in terms of objectives, target users, users’ involvement, usability and accessibility issues, settings to be applied, technologies used and development stages. The results show the need to improve the integration and interoperability of the existing technologies and to promote user-centric developments with a strong involvement of end users, namely in what concerns usability and accessibility issues.

European Portuguese MRI based speech production studies

Knowledge of the speech production mechanism is essential for the development of speech production models and theories. Magnetic resonance imaging delivers high quality images of soft tissues, has multiplanar capacity and allows for the visualization of the entire vocal tract. To our knowledge, there are no complete and systematic magnetic resonance imaging studies of European Portuguese production. In this study, a recently acquired magnetic resonance imaging database including almost all classes of European Portuguese sounds, excluding taps and trills, is presented and analyzed. Our work contemplated not only image acquisition but also the utilization of image processing techniques to allow the exploration of the entire database in a reasonable time. Contours extracted from 2D images, articulatory measures (2D) and area functions are explored and represent valuable information for articulatory synthesis and articulatory phonetics descriptions. Some European Portuguese distinctive characteristics, such as nasality are addressed in more detail. Results relative to oral vowels, nasal vowels and a comparison between both classes are presented. The more detailed information on tract configuration supports results obtained with other techniques, such as EMMA, and allows the comparison of European Portuguese and French nasal vowels articulation, with differences detected at pharyngeal cavity level and velum port opening quotient. A detailed characterization of the central vowels, particularly the [], is presented and compared with classical descriptions. Results for consonants point to the existence of a single positional dark allophone for [l], a more palato-alveolar place of articulation for [@?], a more anterior place of articulation for [@?] relative to [@?], and the use, by our speaker, of a palatal place of articulation for [k]. Some preliminary results concerning coarticulation are also reported. European Portuguese stops revealed less resistant to coarticulatory effects than fricatives. Among all the sounds studied, [@?] and [@?] present the highest resistance to coarticulation. These results follow the main key features found in other studies performed for different languages.

Dynamic language modeling for a daily broadcast news transcription system

When transcribing Broadcast News data in highly inflected languages, the vocabulary growth leads to high out-of-vocabulary rates. To address this problem, we propose a daily and unsupervised adaptation approach which dynamically adapts the active vocabulary and LM to the topic of the current news segment during a multi-pass speech recognition process. Based on texts daily available on the Web, a story-based vocabulary is selected using a morpho-syntatic technique. Using an Information Retrieval engine, relevant documents are extracted from a large corpus to generate a story-based LM. Experiments were carried out for a European Portuguese BN transcription system. Preliminary results yield a relative reduction of 65.2% in OOV and 6.6% in WER.

The International Classification of Functioning, Disability and Health as a conceptual model for the evaluation of environmental factors

Abstract The concept of Design for All emphasizes the impact of the surrounding environment in the individuals functionality. The International Classification of Functioning, Disability and Health brought the concepts of functionality and disability into a comprehensive whole of multiple dimensions of human functioning, such as biological, psychological, social and environmental. In order to contribute to a greater overall functionality of the individual, the use of software and complex systems can be decisive to assist the people with special needs in all areas of life. The paradigm introduced with ICF is inclusive and universal, so it favors not only the old people, but all others, whether they have a limitation or not. The characteristics of Ambient Assisted Living (AAL) are appropriate to fulfill elderly needs. However, the current state of development is still mostly oriented to a technological perspective, where the individuals functionality has not been fully addressed. Under the Living Usability Lab project we have defined a methodology and created some evaluation tools for assessment of AAL services according to a Living Lab perspective, based on the ICF. In this paper we intend to describe the base fundamentals of this proposal, as well as present some results concerning a practical implementation of this methodology.

Elderly Centered Design for Interaction – The Case of the S4S Medication Assistant☆

Abstract Several aspects of older adults’ life can benefit from recent technological developments, but success in harnessing this potential depends on careful design and accessible, easy to use products. Design and development must be centered on the elderly and adequately consider interaction. In this paper we follow this design approach and put it to the test in developing a concrete application, aimed to contribute to lower the high levels of non-adherence to medication in the elderly population. The “Medication Assistant” application was developed following an iterative method centered, from the start, on the elderly and interaction design. The method repeats short-time development cycles integrating definition of scenarios and goals, requirements engineering, design, prototyping and evaluation. Evaluation, by end-users, of the increasingly refined prototypes, is a key characteristic of the method. The evaluation results provide information related to strengths and weaknesses of the application and yield suggestions regarding changes and improvements, valuable support further development. Results regarding evaluation of the second prototype of “Medication Assistant” are presented.

Speech-centric Multimodal Interaction for Easy-to-access Online Services – A Personal Life Assistant for the Elderly

Abstract The PaeLife project is a European industry-academia collaboration whose goal is to provide the elderly with easy access to online services that make their life easier and encourage their continued participation in the society. To reach this goal, the project partners are developing a multimodal virtual personal life assistant (PLA) offering a wide range of services from weather information to social networking. This paper presents the multimodal architecture of the PLA, the services provided by the PLA, and the work done in the area of speech input and output modalities, which play a key role in the application.

Real-Time MRI for portuguese

In this paper, we present a database of synchronized audio and Real-Time Magnetic Resonance Imaging (RT-MRI) in order to study dynamic aspects of the production of European Portuguese (EP) sounds. Currently, data have been acquired from one native speaker of European Portuguese. The speech corpus was primarily designed to investigate nasal vowels in a wide range of phonological contexts, but also includes examples of other EP sounds. The RT-MRI protocol developed for the acquisition of the data is detailed. Midsagittal and oblique images were acquired with a frame rate of 14 frames/s, resulting in a temporal resolution of 72 ms. Different image processing tools (automatic and semi-automatic) applied for inspection and analysis of the data are described. We demonstrate the potential of this database and processing techniques with some illustrative examples of Portuguese nasal vowels, taps, trills and laterals.

Design and Development of Speech Interaction: A Methodology

Using speech in computer interaction is advantageous in many situation and more natural for the user. However, development of speech enabled applications presents, in general, a big challenge when designing the application, regarding the implementation of speech modalities and what the speech recognizer will understand.

ICF Inspired Personas to Improve Development for Usability and Accessibility in Ambient Assisted Living

Abstract Ambient Assisted Living (AAL) is an important research and development area. The acceptance of the AAL paradigm is closely related to the quality of the available systems and services, namely in terms of the user interaction. This means that usability and accessibility are crucial issues. The paper presents how the concepts of the International Classification of Functioning, Disability and Health (ICF) can be used to optimize the role of personas and scenarios in the development and evaluation of AAL systems and services, especially in aspects related with human functioning and health conditions.

Simulation of human speech production applied to the study and synthesis of European Portuguese

A new articulatory synthesizer (SAPWindows), with a modular and flexible design, is described. A comprehensive acoustic model and a new interactive glottal source were implemented. Perceptual tests and simulations made possible by the synthesizer contributed to deepening our knowledge of one of the most important characteristics of European Portuguese, the nasal vowels. First attempts at incorporating models of frication into the articulatory synthesizer are presented, demonstrating the potential of performing fricative synthesis based on broad articulatory configurations. Synthesis of nonsense words and Portuguese words with vowels and nasal consonants is also shown. Despite not being capable of competing with mainstream concatenative speech synthesis, the anthropomorphic approach to speech synthesis, known as articulatory synthesis, proved to be a valuable tool for phonetics research and teaching. This was particularly true for the European Portuguese nasal vowels.