Apropriação da ortografia por escolares do 3o ao 5o ano do ensino fundamental

Pós-graduação em Educação - FFC

Instrumento de avaliação metafonológica para caracterização de escolares com dislexia, transtorno e dificuldades de aprendizagem

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Conversão grafema-fone para um sistema de reconhecimento de voz com suporte a grandes vocabulários para o português brasileiro

O processamento de voz tornou-se uma tecnologia cada vez mais baseada na modelagem automática de vasta quantidade de dados. Desta forma, o sucesso das pesquisas nesta área está diretamente ligado a existência de corpora de domínio público e outros recursos específicos, tal como um dicionário fonético. No Brasil, ao contrário do que acontece para a língua inglesa, por exemplo, não existe atualmente em domínio público um sistema de Reconhecimento Automático de Voz (RAV) para o Português Brasileiro com suporte a grandes vocabulários. Frente a este cenário, o trabalho tem como principal objetivo discutir esforços dentro da iniciativa FalaBrasil [1], criada pelo Laboratório de Processamento de Sinais (LaPS) da UFPA, apresentando pesquisas e softwares na área de RAV para o Português do Brasil. Mais especificamente, o presente trabalho discute a implementação de um sistema de reconhecimento de voz com suporte a grandes vocabulários para o Português do Brasil, utilizando a ferramenta HTK baseada em modelo oculto de Markov (HMM) e a criação de um módulo de conversão grafema-fone, utilizando técnicas de aprendizado de máquina.

Classificação fonética utilizando Boosting e SVM

Para compor um sistema de Reconhecimento Automático de Voz, pode ser utilizada uma tarefa chamada Classificação Fonética, onde a partir de uma amostra de voz decide-se qual fonema foi emitido por um interlocutor. Para facilitar a classificação e realçar as características mais marcantes dos fonemas, normalmente, as amostras de voz são pré- processadas através de um fronl-en'L Um fron:-end, geralmente, extrai um conjunto de parâmetros para cada amostra de voz. Após este processamento, estes parâmetros são insendos em um algoritmo classificador que (já devidamente treinado) procurará decidir qual o fonema emitido. Existe uma tendência de que quanto maior a quantidade de parâmetros utilizados no sistema, melhor será a taxa de acertos na classificação. A contrapartida para esta tendência é o maior custo computacional envolvido. A técnica de Seleção de Parâmetros tem como função mostrar quais os parâmetros mais relevantes (ou mais utilizados) em uma tarefa de classificação, possibilitando, assim, descobrir quais os parâmetros redundantes, que trazem pouca (ou nenhuma) contribuição à tarefa de classificação. A proposta deste trabalho é aplicar o classificador SVM à classificação fonética, utilizando a base de dados TIMIT, e descobrir os parâmetros mais relevantes na classificação, aplicando a técnica Boosting de Seleção de Parâmetros.

Desempenho de escolares de ensino público com e sem dificuldade de aprendizagem em habilidadefonológica, nomeação rápida, leitura e escrita

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Desempenho de escolares com dislexia e transtorno do déficit de atenção e hiperatividade nos processos de leitura

This study aimed to characterize and to compare the performance of students with an interdisciplinary diagnosis of dyslexia and attention deficit hyperactivity disorder (ADHD) in students with good academic performance on the reading processes. Sixty students from both genders, from 2nd to 4th grades of municipal public schools in Marília - SP participated in this study, they were distributed as follows: GI, 20 students with interdisciplinary diagnosis of dyslexia; GII, 20 students with ADHD and GIII, 20 students with good academic performance, paired according to gender, age and grade level with GI and GII. The students were submitted to the application of the assessment of reading processes (PROLEC) composed by four processes: letters identification, lexical, syntactical and semantic. The results highlighted that the students of GIII showed superior performance comparing with GI and GII. There was difference between GI and GII only in low frequency word reading and non words reading of the lexical process. The inferior performance from GI and GII in the PROLEC tests can be justified by the difficulty on the coding and decoding abilities. In ADHD students this difficulty was due to impaired interaction between the visual, linguistic, attention and auditory processing and in the dyslexic students was due to failure at the phonological mediation process, which depends on the knowledge of rules of grapheme - phoneme conversion to the acquisition of word reading. These changes affect the reading achievement and the comprehension of the read text.

A escrita de /an/ por pré escolares: pistas acústico-auditivas

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The phonological and visual basis of developmental dyslexia in Brazilian Portuguese reading children

Evidence from opaque languages suggests that visual attention processing abilities in addition to phonological skills may act as cognitive underpinnings of developmental dyslexia. We explored the role of these two cognitive abilities on reading fluency in Brazilian Portuguese, a more transparent orthography than French or English. Sixty-six children with developmental dyslexia and normal Brazilian Portuguese children participated. They were administered three tasks of phonological skills (phoneme identification, phoneme, and syllable blending) and three visual tasks (a letter global report task and two non-verbal tasks of visual closure and visual constancy). Results show that Brazilian Portuguese children with developmental dyslexia are impaired not only in phonological processing but further in visual processing. The phonological and visual processing abilities significantly and independently contribute to reading fluency in the whole population. Last, different cognitively homogeneous subtypes can be identified in the Brazilian Portuguese population of children with developmental dyslexia. Two subsets of children with developmental dyslexia were identified as having a single cognitive disorder, phonological or visual; another group exhibited a double deficit and a few children showed no visual or phonological disorder. Thus the current findings extend previous data from more opaque orthographies as French and English, in showing the importance of investigating visual processing skills in addition to phonological skills in children with developmental dyslexia whatever their language orthography transparency.

Caracterização do desempenho de escolares com e sem dificuldades de aprendizagem em tarefas de consciência fonológica

Learning to read and write at an early stage is the process of transferring the sound form of the spoken language for the graphical form of writing, a process, a time that in our system of alphabetical called writing, the letters are graphical representations in the level of phoneme. So that this representation occurs, it is necessary that the individual already can of some form perceive and manipulate the different sonorous segments of the word. This capacity of perception directed to the segments of the word calls Phonological Awareness. Thus, it was established had for objective to verify the pertaining to school performance of 1ª to 4ª series with and without of learning in Tests of Phonological Awareness. Fourth children with age average of 9 years and 3 months without learning disabilities had been submitted to the Protocol of Phonological Awareness (CIELO, 2002) using of this instrument had participated of this study 80 pertaining to school of both only the phonological tasks. The data received from quantiqualitative approach whose results were extracted inferences. The statistically significant results occurred in the tasks of Realism Face Detection, Syllables, Detecting Phonemes, Phonemic Synthesis and Reversal Phonemic. Based on the results we observed that children without learning difficulties performed better on all tasks mentioned above

A influência da ortografia na percepção e produção do inglês como língua estrangeira

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Relação entre as habilidades metalinguísticas, leitura e compreensão leitora em escolares com Transtorno do Déficit de Atenção com Hiperatividade

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Modelo de Resposta à Intervenção (RTI) para desenvolvimento das habilidades fonológicas com tutoria instrucional em contexto escolar: elaboração e controle de eficácia

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Transposições ortográficas e estrutura da sílaba na escrita infantil

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Neurolinguistic analysis: aspects of language and speech deviations in Palestinian Arabic aphasics

The characteristics of aphasics’ speech in various languages have been the core of numerous studies, but Arabic in general, and Palestinian Arabic in particular, is still a virgin field in this respect. However, it is of vital importance to have a clear picture of the specific aspects of Palestinian Arabic that might be affected in the speech of aphasics in order to establish screening, diagnosis and therapy programs based on a clinical linguistic database. Hence the central questions of this study are what are the main neurolinguistic features of the Palestinian aphasics’ speech at the phonetic-acoustic level and to what extent are the results similar or not to those obtained from other languages. In general, this study is a survey of the most prominent features of Palestinian Broca’s aphasics’ speech. The main acoustic parameters of vowels and consonants are analysed such as vowel duration, formant frequency, Voice Onset Time (VOT), intensity and frication duration. The deviant patterns among the Broca’s aphasics are displayed and compared with those of normal speakers. The nature of deficit, whether phonetic or phonological, is also discussed. Moreover, the coarticulatory characteristics and some prosodic patterns of Broca’s aphasics are addressed. Samples were collected from six Broca’s aphasics from the same local region. The acoustic analysis conducted on a range of consonant and vowel parameters displayed differences between the speech patterns of Broca’s aphasics and normal speakers. For example, impairments in voicing contrast between the voiced and voiceless stops were found in Broca’s aphasics. This feature does not exist for the fricatives produced by the Palestinian Broca’s aphasics and hence deviates from data obtained for aphasics’ speech from other languages. The Palestinian Broca’s aphasics displayed particular problems with the emphatic sounds. They exhibited deviant coarticulation patterns, another feature that is inconsistent with data obtained from studies from other languages. However, several other findings are in accordance with those reported from various other languages such as impairments in the VOT. The results are in accordance with the suggestions that speech production deficits in Broca’s aphasics are not related to phoneme selection but rather to articulatory implementation and some speech output impairments are related to timing and planning deficits.

Corpus-Based Speech Enhancement With Uncertainty Modeling and Cepstral Smoothing

We present a new approach for corpus-based speech enhancement that significantly improves over a method published by Xiao and Nickel in 2010. Corpus-based enhancement systems do not merely filter an incoming noisy signal, but resynthesize its speech content via an inventory of pre-recorded clean signals. The goal of the procedure is to perceptually improve the sound of speech signals in background noise. The proposed new method modifies Xiao's method in four significant ways. Firstly, it employs a Gaussian mixture model (GMM) instead of a vector quantizer in the phoneme recognition front-end. Secondly, the state decoding of the recognition stage is supported with an uncertainty modeling technique. With the GMM and the uncertainty modeling it is possible to eliminate the need for noise dependent system training. Thirdly, the post-processing of the original method via sinusoidal modeling is replaced with a powerful cepstral smoothing operation. And lastly, due to the improvements of these modifications, it is possible to extend the operational bandwidth of the procedure from 4 kHz to 8 kHz. The performance of the proposed method was evaluated across different noise types and different signal-to-noise ratios. The new method was able to significantly outperform traditional methods, including the one by Xiao and Nickel, in terms of PESQ scores and other objective quality measures. Results of subjective CMOS tests over a smaller set of test samples support our claims.