ESSA - TF - Congressos e eventos científicos (inclui comunicações e posters em atas de conferências/encontros científicos)
Permanent URI for this collection
Browse
Browsing ESSA - TF - Congressos e eventos científicos (inclui comunicações e posters em atas de conferências/encontros científicos) by Issue Date
Now showing 1 - 10 of 17
Results Per Page
Sort Options
- “To talk or not to talk”- an rTMS study about naming during stimulationPublication . Tello Rodrigues, Inês; Castelo-Branco, M; Castro-Caldas, Alexandre
- Robust phoneme recognition for a speech therapy environmentPublication . Grossinho, André; Guimarães, Isabel; Magalhães, João; Cavaco, SofiaTraditional speech therapy approaches for speech sound disorders have a lot of advantages to gain from computerbased therapy systems. With speech recognition techniques the motivation elements of these systems can be automated in order to get an interactive environment that motivates the therapy attendee towards better performances. Here we propose a robust phoneme recognition solution for an interactive environment for speech therapy. We compare the results of hierarchical and flat classification, with naive Bayes, support vector machines andkernel density estimation on linear predictive coding coefficients and Mel-frequency cepstral coefficients.
- 3D facial video retrieval and management for decision support in speech and language therapyPublication . Carrapiço, Ricardo; Guimarães, Isabel; Grilo, Ana Margarida; Cavaco, Sofia; Magalhães, João3D video is introducing great changes in many health related areas. The realism of such information provides health professionals with strong evidence analysis tools to facilitate clinical decision processes. Speech and language therapy aims to help subjects in correcting several disorders. The assessment of the patient by the speech and language therapist (SLT), requires several visual and audio analysis procedures that can interfere with the patient's production of speech. In this context, the main contribution of this paper is a 3D video system to improve health information management processes in speech and language therapy. The 3D video retrieval and management system supports multimodal health records and provides the SLTs with tools to support their work in many ways: (i) it allows SLTs to easily maintain a database of patients' orofacial and speech exercises; (ii) supports three-dimensional orofacial measurement and analysis in a non-intrusive way; and (iii) search patient speech-exercises by similar facial characteristics, using facial image analysis techniques. The second contribution is a dataset with 3D videos of patients performing orofacial speech exercises. The whole system was evaluated successfully in a user study involving 22 SLTs. The user study illustrated the importance of the retrieval by similar orofacial speech exercise.
- Automatic detection of Parkinson’s disease: an experimental analysis of common speech production tasks used for diagnosisPublication . Pompili, Anna; Abad, Alberto; Romano, Paolo; Martins, Isabel P; Cardoso, Rita; Santos, Helena; Carvalho, Joana; Guimarães, Isabel; Ferreira, JoaquimParkinson’s disease (PD) is the second most common neurodegenerative disorder of mid-to-late life after Alzheimer’s disease. During the progression of the disease, most individuals with PD report impairments in speech due to deficits in phonation, articulation, prosody, and fluency. In the literature, several studies perform the automatic classification of speech of people with PD considering various types of acoustic information extracted from different speech tasks. Nevertheless, it is unclear which tasks are more important for an automatic classification of the disease. In this work, we compare the discriminant capabilities of eight verbal tasks designed to capture the major symptoms affecting speech. To this end, we introduce a new database of Portuguese speakers consisting of 65 healthy control and 75 PD subjects. For each task, an automatic classifier is built using feature sets and modeling approaches in compliance with the current state of the art. Experimental results permit to identify reading aloud prosodic sentences and story-telling tasks as the most useful for the automatic detection of PD.
- 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.
- 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.
- 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.
- Speech sounds data for typically developing european portuguese children 6-9 years oldPublication . Guimarães, Isabel; Ascensão, Mariana; Grilo, Ana MargaridaPurposes: To identify the European Portuguese (EP) speech sounds competence in children. Methods: A total of 240 children between 6 and 9;11 years old named 37 pictures. Gender and age effect as well as the age limit for EP speech sound mastery were analyzed. The percentage of consonants correct (PCC) were determined. The criteria used were PCC ≥75% (acquired sound) and ≥90% (mastered sound). Results: No gender effect for speech sound development was found in the studied age range. Children with older ages [8-9;11] showed a slightly significant mean performance than younger ages [6-7;11]. The girls appeared to reach higher mean competence than boys; however, gender effect did not reach significance. At the [6-6;11] years old age range all plosives (except the word-medial /t/ and /g/), four fricatives (/f/, /v/, word-initial /ʃ/ and word-medial /Ʒ/) and two laterals (word-medial /r/ and word-initial and medial /R/) are mastered. The other targeted sounds are mastered either at the [7-7;11] or at the [8-8;11] year old range. Conclusion: The EP targeted speech sounds are mastered between 6 and 8;11 years old.
- 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.