ESSA - TF - Congressos e eventos científicos (inclui comunicações e posters em atas de conferências/encontros científicos)
Permanent URI for this collection
Browse
Recent Submissions
- SEMantic and PRAgmatic assessment platform for school-age childrenPublication . Tavares, Maria Dulce; Sua Kay, EileenBackground: Semantic and pragmatic skills are developed throughout life and are essential in the development of school and social learning. Upon entering school, learning to read and write is developed in two large areas of knowledge. The first implies capacities of recognition and decoding of written symbols of the word and vocabulary development and the second allows the understanding of what is read through inferential capacities and non-literal interpretation. Often, students with reading comprehension difficulties go unnoticed. It is easier to detect a child who reads slowly, syllable by syllable, or with mistakes than those who read fluently but without understanding the content. These difficulties only become evident when questions are asked about the text and when it is necessary to understand the questions of subjects such as mathematics or science. Thus, success to reach the National Curricular Plan can be compromised. Methods: Material was developed to evaluate semantic and pragmatic skills in school-aged children. In semantics, aspects of syntagmatic and paradigmatic relations (lexical field, synonymy and antonyms) and paronymy are evaluated. In pragmatics, competences are evaluated such as inferences, comprehension of idioms and proverbs. This material will be placed on a platform that can be consulted and used by different professionals working with children. The items that constitute this material took into account the stages of language development and school level. The lexicon used is in the domain of European Portuguese. Results: The 756 children who were assessed attended public and private schools in Portugal. The results show an increasing evolution of the lexical competences of the children, with significant differences between the different age groups in all tests. There were no significant differences between female and male except in the paronym test. Regarding the socio-professional level of the child's origin, it is verified that it is a differentiating factor of lexical competence because significant differences in all tests were observed regardless of the age of the child. Conclusions: The authors concluded that it is of great importance to analyse lexical competence regarding the aspects of its organization, as it enables students to deal with academic tasks successfully, improving literacy as well as to be able to act in a systematic and productive way in the intervention with children with language disorders. The complexity and innovation of the pragmatic skills assessment (in European Portuguese) leads to this work to continue in development.
- A model for sibilant distortion detection in childrenPublication . Anjos, Ivo; Grilo, Ana Margarida; Ascensão, Mariana; Guimarães, Isabel; Magalhães, João; Cavaco, SofiaThe distortion of sibilant sounds is a common type of speech sound disorder in European Portuguese speaking children. Speech and language pathologists (SLP) use different types of speech production tasks to assess these distortions. One of these tasks consists of the sustained production of isolated sibilants. Using these sound productions, SLPs usually rely on auditory perceptual evaluation to assess the sibilant distortions. Here we propose to use an isolated sibilant machine learning model to help SLPs assessing these distortions. Our model uses Mel frequency cepstral coefficients of the isolated sibilant phones and it was trained with data from 145 children. The analysis of the false negatives detected by the model can give insight into whether the child has a sibilant production distortion. We were able to confirm that there exist some relation between the model classification results and the distortion assessment of professional SLPs. Approximately 66% of the distortion cases identified by the model are confirmed by an SLP as having some sort of distortion or are perceived as being the production of a different sound.
- Aprendizagem ao longo da vida e desenvolvimento profissional contínuo do terapeuta da fala em perturbações da fluênciaPublication . Carmona, JaquelineIntrodução: Análise de conceções sobre aprendizagem ao longo da vida (ALV) e sobre desenvolvimento profissional contínuo (DPC). Propomos contribuir para o amplificar da reflecção sobre o que ALV abarca: conferente de grau académico, ALV formal e ALV informal. Será explanado o paradigma de DPC conforme recomendado pela Organização das Nações Unidas para a Educação Ciência e a Cultura (UNESCO), Organização para a Cooperação e Desenvolvimento Económico (OCDE), pela União Europeia (EU), assim como pela European Speech and Language Therapy Association (ESLA) e pela Associação Portuguesa de Terapeutas da Fala (APTF). Objetivos: Pretende-se enunciar como o terapeuta da fala (TF) pode conceptualizar estes processos tendo em conta a especificidade e as competências necessárias na área das perturbações da fluência (PF). Metodologia: Foi realizada uma revisão da literatura. Foram consultadas fontes não periódicas, legislação e artigos científicos desde a origem da profissão em Portugal até 2020. Resultados e conclusão: A terapia da fala é uma profissão em evolução, uma área científica cujo conhecimento deriva das ciências da saúde e das ciências humanas e aplicadas. Abrange um vasto leque de conhecimentos que permitem a polivalência de atuação, face à sua vasta abrangência existe a necessidade de especialização.
- Tradução e adaptação do conteúdo da COCAF-4 para o Português EuropeuPublication . Trindade, Beatriz; Gomes, Inês; Jorge, Maria; Pimpão, Matilde; Lopes, Inês; Soares, Elsa Marta
- Lateralization of the visual word form area in patients with alexia after strokePublication . Tello Rodrigues, Inês; Canário, Nádia; Castro-Caldas, AlexandreBackground Knowledge of the process by which visual information is integrated into the brain reading system promotes a better understanding of writing and reading models. Objective This study aimed to use functional Magnetic Resonance Imaging (fMRI) to explore whether the Blood-oxygen-level dependent (BOLD) contrast imaging patterns, of putative cortical region of the Visual Word Form Area (VWFA), are distinct in aphasia patients with moder- ate and severe alexia. Methods Twelve chronic stroke patients (5 patients with severe alexia and 7 pa- tients with moderate alexia) were included. A word categorization task was used to examine responses in the VWFA and its right homolog re- gion. Patients performed a semantic decision task in which words were contrasted with non-verbal fonts to assess the lateralization of reading ability in the ventral occipitotemporal region. Results A fixed effects (FFX) general linear model (GLM) multi-study from the contrast of patients with moderate alexia and those with severe alexia (FDR, p = 0.05, corrected for multiples comparisons using a Threshold Estimator plugin (1000 Monte Carlo simulations), was per- formed. Activation of the left VWFA was robust in patients with mod- erate alexia. Aphasia patients with severe reading deficits also activated the right homolog VWFA. Conclusions This bilateral activation pattern only in patients with severe alexia could be interpreted as a result of reduced recruitment of the left VWFA for reading tasks due to the severe reading deficit. This study provides some new insights about reading pathways and possible neuroplasti- city mechanisms in aphasia patients with alexia. Additional reports could explore the predictive value of right VWFA activation for reading recovery and aid language therapy in patients with aphasia.
- “To talk or not to talk”- an rTMS study about naming during stimulationPublication . Tello Rodrigues, Inês; Castelo-Branco, M; Castro-Caldas, Alexandre
- Assessment of Parkinson’s disease medication state through automatic speech analysisPublication . Pompili, Anna; Solera-Urena, Rubén; Abad, Alberto; Cardoso, Rita; Guimarães, Isabel; Fabbri, Margherita; Martins, Isabel P; Ferreira, JoaquimParkinson’s disease (PD) is a progressive degenerative disorder of the central nervous system characterized by motor and nonmotor symptoms. As the disease progresses, patients alternate periods in which motor symptoms are mitigated due to medication intake (ON state) and periods with motor complications (OFF state). The time that patients spend in the OFF condition is currently the main parameter employed to assess pharmacological interventions and to evaluate the efficacy of different active principles. In this work, we present a system that combines automatic speech processing and deep learning techniques to classify the medication state of PD patients by leveraging personal speech-based bio-markers. We devise a speakerdependent approach and investigate the relevance of different acoustic-prosodic feature sets. Results show an accuracy of 90.54% in a test task with mixed speech and an accuracy of 95.27% in a semi-spontaneous speech task. Overall, the experimental assessment shows the potentials of this approach towards the development of reliable, remote daily monitoring and scheduling of medication intake of PD patients.
- A serious mobile game with visual feedback for training sibilant consonantsPublication . Anjos, Ivo; Grilo, Ana Margarida; Ascensão, Mariana; Guimarães, Isabel; Magalhães, João; Cavaco, SofiaAbstract. The distortion of sibilant sounds is a common type of speech sound disorder (SSD) in Portuguese speaking children. Speech and language pathologists (SLP) frequently use the isolated sibilants exercise to assess and treat this type of speech errors. While technological solutions like serious games can help SLPs to motivate the children on doing the exercises repeatedly, there is a lack of such games for this specic exercise. Another important aspect is that given the usual small number of therapy sessions per week, children are not improving at their maximum rate, which is only achieved by more intensive therapy. We propose a serious game for mobile platforms that allows children to practice their isolated sibilants exercises at home to correct sibilant distortions. This will allow children to practice their exercises more frequently, which can lead to faster improvements. The game, which uses an automatic speech recognition (ASR) system to classify the child sibilant productions, is controlled by the child's voice in real time and gives immediate visual feedback to the child about her sibilant productions. In order to keep the computation on the mobile platform as simple as possible, the game has a client-server architecture, in which the external server runs the ASR system. We trained it using raw Mel frequency cepstral coe cients, and we achieved very good results with an accuracy test score of above 91% using support vector machines.
- Sibilant consonants classification with deep neural networksPublication . Anjos, Ivo; Marques, Nuno; Grilo, Ana Margarida; Guimarães, Isabel; Magalhães, João; Cavaco, SofiaAbstract. Many children su ering from speech sound disorders cannot pronounce the sibilant consonants correctly. We have developed a serious game that is controlled by the children's voices in real time and that allows children to practice the European Portuguese sibilant consonants. For this, the game uses a sibilant consonant classi er. Since the game does not require any type of adult supervision, children can practice the production of these sounds more often, which may lead to faster improvements of their speech. Recently, the use of deep neural networks has given considerable improvements in classi cation for a variety of use cases, from image classication to speech and language processing. Here we propose to use deep convolutional neural networks to classify sibilant phonemes of European Portuguese in our serious game for speech and language therapy. We compared the performance of several diferent arti cial neural networks that used Mel frequency cepstral coefcients or log Mel lterbanks. Our best deep learning model achieves classi cation scores of 95:48% using a 2D convolutional model with log Mel lterbanks as input features.
- The BioVisualSpeech european portuguese sibilants corpusPublication . Grilo, Ana Margarida; Guimarães, Isabel; Ascensão, Mariana; Abad, Alberto; Anjos, Ivo; Magalhães, João; Cavaco, SofiaAbstract. The development of reliable speech therapy computer tools that automatically classify speech productions depends on the quality of the speech data set used to train the classi cation algorithms. The data set should characterize the population in terms of age, gender and native language, but it should also have other important properties that characterize the population that is going to use the tool. Thus, apart from including samples from correct speech productions, it should also have samples from people with speech disorders. Also, the annotation of the data should include information on whether the phonemes are correctly or wrongly pronounced. Here, we present a corpus of European Portuguese children's speech data that we are using in the development of speech classi ers for speech therapy tools for Portuguese children. The corpus includes data from children with speech disorders and in which the labelling includes information about the speech production errors. This corpus, which has data from 356 children from 5 to 9 years of age, focuses on the European Portuguese sibilant consonants and can be used to train speech recognition models for tools to assist the detection and therapy of sigmatism.