Browsing by Author "Lopes, Carla"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
- Automatic evaluation of reading aloud performance in childrenPublication . Proença, Jorge; Lopes, Carla, Alexandra Calado Lopes; Tjalve, Michael; Stolcke, Andreas; Candeias, Sara; Perdigão, FernandoEvaluating children’s reading aloud proficiency is typically a task done by teachers on an individual ba sis, where reading time and wrong words are marked manually. A computational tool that assists with recording reading tasks, automatically analyzing them and outputting performance related metrics could be a significant help to teachers. Working towards that goal, this work presents an approach to automat ically predict the overall reading aloud ability of primary school children by employing automatic speech processing methods. Reading tasks were designed focused on sentences and pseudowords, so as to obtain complementary information from the two distinct assignments. A dataset was collected with recordings of 284 children aged 6–10 years reading in native European Portuguese. The most common disfluencies identified include intra-word pauses, phonetic extensions, false starts, repetitions, and mispronunciations. To automatically detect reading disfluencies, we first target extra events by employing task-specific lat tices for decoding that allow syllable-based false starts as well as repetitions of words and sequences of words. Then, mispronunciations are detected based on the log likelihood ratio between the recognized and target words. The opinions of primary school teachers were gathered as ground truth of overall read ing aloud performance, who provided 0–5 scores closely related to the expected performance at the end of each grade. To predict these scores, various features were extracted by automatic annotation and re gression models were trained. Gaussian process regression proved to be the most successful approach. Feature selection from both sentence and pseudoword tasks give the closest predictions, with a correla tion of 0.944 compared to the teachers’ grading. Compared to the use of manual annotation, where the best models obtained give a correlation of 0.949, there was a relative decrease of only 0.5% for using automatic annotations to extract features. The error rate of predicted scores relative to ground truth also proved to be smaller than the deviation of evaluators’ opinion per child.
- A hierarchical broad-class classification to enhance phoneme recognitionPublication . Lopes, Carla, Alexandra Calado Lopes; Perdigão, FernandoIn this paper a hierarchical classification of different levels of phonetic information is proposed in order to improve phone recognition. In this paradigm several intermediate classifiers give posterior probability predictions for broad phonetic classes, achieving phone detail in the last layer. Class membership probabilities are weighted and combined in order to get a more robust phoneme prediction. A method for finding the best set of weights is also proposed based on discriminative training in a hybrid MLP/HMM system. Experiments show that the use of broad-class information enhances phone recognition. Relative improvements of 8% in Correctness and 5% in Accuracy were achieved in phoneme recognition on the TIMIT database compared to a baseline system.
- The LetsRead Corpus of Portuguese children reading aloud for performance evaluationPublication . Proença, Jorge; Celorico, Dirce; Candeias, Sara; Lopes, Carla; Perdigão, FernandoThis paper introduces the LetsRead Corpus of European Portuguese read speech from 6 to 10 years old children. The motivation for the creation of this corpus stems from the inexistence of databases with recordings of reading tasks of Portuguese children with different performance levels and including all the common reading aloud disfluencies. It is also essential to develop techniques to fulfill the main objective of the LetsRead project: to automatically evaluate the reading performance of children through the analysis of reading tasks. The collected data amounts to 20 hours of speech from 284 children from private and public Portuguese schools, with each child carrying out two tasks: reading sentences and reading a list of pseudowords, both with varying levels of difficulty throughout the school grades. In this paper, the design of the reading tasks presented to children is described, as well as the collection procedure. Manually annotated data is analyzed according to disfluencies and reading performance. The considered word difficulty parameter is also confirmed to be suitable for the pseudoword reading tasks.
- Prospetiva 2035 - Três Cenários para o Futuro de Leiria e OestePublication . Silva, Agostinho da; Lopes, Carla; Almeida, Isabel; Carriço, Silvia; Mouga, Teresa; Carriço, Silvia; Siopa, Jorge; Gala, Pedro; Antunes, Mário; Silva, Agostinho; Mouga, Teresa; Lopes, Carla, Alexandra Calado Lopes; Gala, Pedro; Siopa, JorgeA EM@IPLeiria é um think tank criado em 2023 para impulsionar um desenvolvimento sustentável, inovador e competitivo na região de Leiria e Oeste. Mais do que um centro de estudos, é uma fábrica de ideias e soluções, dedicada à análise dos desafios estruturais do território, à identificação de novas oportunidades e ao teste de respostas concretas para problemas reais. Como espaço de cocriação e experimentação, a EM@IPLeiria envolve diversos atores regionais, incluindo autarquias, empresas, instituições de ensino e a sociedade civil, promovendo um modelo de trabalho colaborativo e participativo na construção de estratégias para o futuro. A sua abordagem alia design thinking e prospetiva estratégica, permitindo antecipar tendências, conceber cenários e testar soluções inovadoras antes da sua aplicação em larga escala.
- Validation of the Telephone-Administered Version of the Mediterranean Diet Adherence Screener (MEDAS) QuestionnairePublication . Gregório, Maria João; Rodrigues, Ana M.; Salvador, Clara; Dias, Sara S.; Sousa, Rute D. de; Mendes, Jorge M.; Coelho, Pedro S.; Branco, Jaime C.; Lopes, Carla; Martínez-González, Miguel A.; Graça, Pedro; Canhão, HelenaA 14-Item Mediterranean Diet Adherence Screener (MEDAS) questionnaire was developed and validated in face-to-face interviews, but not via telephone. The aims of this study were to evaluate the validity and reliability of a telephone-administered version of the MEDAS as well as to validate the Portuguese version of the MEDAS questionnaire. A convenience community-based sample of adults (n = 224) participated in a three-stage survey. First, trained researchers administered MEDAS via a telephone. Second, the Portuguese version of Food Frequency Questionnaire (FFQ), and MEDAS were administered in a semi-structured face-to-face interview. Finally, MEDAS was again administered via telephone. The telephone-administered MEDAS questionnaire was compared with the face-to-face-version using several metrics. The telephone-administered MEDAS was significantly correlated with the face-to-face-administered MEDAS [r = 0.805, p < 0.001; interclass correlation coefficient (ICC) = 0.803, p < 0.001] and showed strong agreement (k = 0.60). The MEDAS scores that were obtained in the first and second telephone interviews were significantly correlated (r = 0.661, p < 0.001; ICC = 0.639, p < 0.001). The overall agreement between the Portuguese version of MEDAS and the FFQ-derived Mediterranean diet adherence score had a Cohen's k = 0.39. The telephone-administered version of MEDAS is a valid tool for assessing the adherence to the Mediterranean diet and acquiring data for large population-based studies.