967 resultados para Speaker Recognition, Text-constrained, Multilingual, Speaker Verification, HMMs


Relevância:

30.00% 30.00%

Publicador:

Resumo:

This essay examines the case of the direct object in Russian sentences with the negated verbs не видеть and не знать. For each verb, 50 contexts were downloaded from the newspaper corpus of the Russian National Corpus and analysed with respect to the semantic properties of the direct object and the negated verb. The theories and concepts used for the analysis have been outlined in Padutjeva, 2006. The analysis of не видеть suggests that the main difference between the genitive and the ac-cusative case is to be found in the notion of non-existence or absence implicated by the verb’s semantics. In utterances with не видеть as a predicate, this notion is always present and is expressed by the genitive case. The speaker may also choose to ignore it by using the accusa-tive and thus emphasize some other aspect of the described situation. The examined properties of reference, definiteness and denotative status of the direct object seem to play a secondary role for how case is used. Their influence is to delimit the meaning of the objective genitive to either non-existence or absence. No similar conclusions could be drawn from the examination of не знать. The reason for this is that the concept of private sphere, used by Padutjeva to explain the use of objective geni-tive with this verb, could not be properly established during the analysis. Just as the notion of absence is crucial for the understanding of the objective genitive when it occurs with не видеть, the concept private sphere seems to be the key to understand it when it occurs with не знать.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This paper presents a computer-vision based marker-free method for gait-impairment detection in Patients with Parkinson's disease (PWP). The system is based upon the idea that a normal human body attains equilibrium during the gait by aligning the body posture with Axis-of-Gravity (AOG) using feet as the base of support. In contrast, PWP appear to be falling forward as they are less-able to align their body with AOG due to rigid muscular tone. A normal gait exhibits periodic stride-cycles with stride-angle around 45o between the legs, whereas PWP walk with shortened stride-angle with high variability between the stride-cycles. In order to analyze Parkinsonian-gait (PG), subjects were videotaped with several gait-cycles. The subject's body was segmented using a color-segmentation method to form a silhouette. The silhouette was skeletonized for motion cues extraction. The motion cues analyzed were stride-cycles (based on the cyclic leg motion of skeleton) and posture lean (based on the angle between leaned torso of skeleton and AOG). Cosine similarity between an imaginary perfect gait pattern and the subject gait patterns produced 100% recognition rate of PG for 4 normal-controls and 3 PWP. Results suggested that the method is a promising tool to be used for PG assessment in home-environment.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

MENDES, Jean Joubert Freitas. Renovando os sentidos: percepção e escrita etnográfica na etnomusicologia. In: ANPPOM, 17. Rio de Janeiro, 2005. Anais... Rio de Janeiro: UFRN/ANPPOM, 2005.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

This body of work aims to describe and analyze the behavior of the Aí specificity marker of indefinite Noun Phrases (NP), one of the many functions this linguistic item is developing in contemporary Brazilian Portuguese. From the Functional Linguistic theory perspective, the North American declivity, this project intends to outline the possible grammaticalization trajectory taken by the Aí specificity marker. It will be followed from its function as a spatial deitic up to its integration of indefinite NP, and the action of the fundamental principles of the theory, such as iconicity and informativity, will be observed on the use of this item. Following this, Aí specificity marker behavior will be described in respect to various linguistic and social factors: type of text where the occurrence is encountered, language modality in which the latter is produced, syntactic function developed by the NP specified by Aí , the existence or lack of material intervening between Aí and the NP nuclear noun, informational status of the NP adjugated to Aí , and finally, sex, education and age of the speaker. The occurrence of conversational implicatures will also be verified (GRICE, 1982) within the contexts of Aí specificity marker use. Reflections on the teaching of grammar will be made, as well as on the possibility and validity of working with noun phrase specificity markers in elementary and high school Portuguese language classes. The data used in this research project stem from Corpus Discurso & Gramática A língua falada e escrita na cidade do Natal (FURTADO DA CUNHA, 1998), and from Corpus Discurso & Gramática A língua falada e escrita na cidade do Rio de Janeiro (VOTRE; OLIVEIRA, 1995)

Relevância:

30.00% 30.00%

Publicador:

Resumo:

In this work, the argumentative strategies construction in university entrance examinations texts is analyzed. The study intended to present, through the analyzed occurrences in the corpus, the discursive strategies use for the argumentation construction, observing the different lexicalization forms and the effects that these strategies produced for the intended meaning construction. Aiming to analyze the modalization via texts written by candidates for the UFRN entrance examination, the relations between this category and the resources used for the argumentative guidance of the text were highlighted. Conceived as a speaker argumentative strategy to express his/her relationship with the proposition content which enunciates, the modalization is, thus, one of the linguistic expression form used for the attainment of intended meaning effects in the argumentation construction. In order to substantiate the research, the theoretical assumptions adopted were the propositions which deal with this linguistic category, guiding it to a pragmatic-semantic perspective as well as a discursive-semantic one. Hence, Neves ( 1996, 2006), Koch ( 2000, 2002), Cervoni ( 1989), Bronkart (1999) and Castilho; Morais de Castilho (1996) studies, among others founded this work. Afterwards, a contextualized analysis of the modalized statements, taking into account all the set of elements implied on the argumentation construction, was carried out. The research, which had a strict qualitative character, revealed that the candidates make use of modalization to express commitment or dissociation as regards the statement which they produce; to obtain credibility and provide more authority to their arguments, thus avoiding them of being contested; to impose their arguments as real ones and acquire acceptance of the interlocutor; to lessen the proposition content and disguise the knowledge source; to comment the enunciation and attribute the discourse to another sender; to establish a dialogic relation with the interlocutor. In addition to offering support for new investigations, the research also aims to contribute for the mother tongue teaching, emphasizing the need of a focus which provides special attention to the written language functioning and its application diversity. In this work, the argumentative strategies construction in university entrance examinations texts is analyzed. The study intended to present, through the analyzed occurrences in the corpus, the discursive strategies use for the argumentation construction, observing the different lexicalization forms and the effects that these strategies produced for the intended meaning construction. Aiming to analyze the modalization via texts written by candidates for the UFRN entrance examination, the relations between this category and the resources used for the argumentative guidance of the text were highlighted. Conceived as a speaker argumentative strategy to express his/her relationship with the proposition content which enunciates, the modalization is, thus, one of the linguistic expression form used for the attainment of intended meaning effects in the argumentation construction. In order to substantiate the research, the theoretical assumptions adopted were the propositions which deal with this linguistic category, guiding it to a pragmatic-semantic perspective as well as a discursive-semantic one. Hence, Neves ( 1996, 2006), Koch ( 2000, 2002), Cervoni ( 1989), Bronkart (1999) and Castilho; Morais de Castilho (1996) studies, among others founded this work. Afterwards, a contextualized analysis of the modalized statements, taking into account all the set of elements implied on the argumentation construction, was carried out. The research, which had a strict qualitative character, revealed that the candidates make use of modalization to express commitment or dissociation as regards the statement which they produce; to obtain credibility and provide more authority to their arguments, thus avoiding them of being contested; to impose their arguments as real ones and acquire acceptance of the interlocutor; to lessen the proposition content and disguise the knowledge source; to comment the enunciation and attribute the discourse to another sender; to establish a dialogic relation with the interlocutor. In addition to offering support for new investigations, the research also aims to contribute for the mother tongue teaching, emphasizing the need of a focus which provides special attention to the written language functioning and its application diversity

Relevância:

30.00% 30.00%

Publicador:

Resumo:

O presente texto é o discurso de paraninfo pronunciado para os formandos da turma de 2001 da Faculdade de Filosofia e Ciências da Universidade Estadual Paulista, Campus de Marília/SP. Constitui-se em pequena reflexão sobre o momento da formatura, a passagem para a vida profissional e os problemas mais candentes que a vida acadêmica enfrenta hoje no Brasil.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

A body of research has developed within the context of nonlinear signal and image processing that deals with the automatic, statistical design of digital window-based filters. Based on pairs of ideal and observed signals, a filter is designed in an effort to minimize the error between the ideal and filtered signals. The goodness of an optimal filter depends on the relation between the ideal and observed signals, but the goodness of a designed filter also depends on the amount of sample data from which it is designed. In order to lessen the design cost, a filter is often chosen from a given class of filters, thereby constraining the optimization and increasing the error of the optimal filter. To a great extent, the problem of filter design concerns striking the correct balance between the degree of constraint and the design cost. From a different perspective and in a different context, the problem of constraint versus sample size has been a major focus of study within the theory of pattern recognition. This paper discusses the design problem for nonlinear signal processing, shows how the issue naturally transitions into pattern recognition, and then provides a review of salient related pattern-recognition theory. In particular, it discusses classification rules, constrained classification, the Vapnik-Chervonenkis theory, and implications of that theory for morphological classifiers and neural networks. The paper closes by discussing some design approaches developed for nonlinear signal processing, and how the nature of these naturally lead to a decomposition of the error of a designed filter into a sum of the following components: the Bayes error of the unconstrained optimal filter, the cost of constraint, the cost of reducing complexity by compressing the original signal distribution, the design cost, and the contribution of prior knowledge to a decrease in the error. The main purpose of the paper is to present fundamental principles of pattern recognition theory within the framework of active research in nonlinear signal processing.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, ε, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine ε, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm. © 2010 IEEE.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

30.00% 30.00%

Publicador:

Resumo:

A fala apresenta aspectos paralinguísticos que não pertencem ao código linguístico convencional, mas contribuem significativamente para a unidade temática do discurso, Essas realizações se constituem em enunciados não-lexicalizados que funcionam que funcionam como atos de fala completos nas interações comunicativas interpessoais. Sobre essas emissões não-verbais, Campbell (2002a, 2002b, 2003 e 2004), Maekawa (2004), Fujie et. al (2004), Hoult (2004), Key (1958) apud Steimberg (1988) postulam que elas constribuem para a manifestação da fala expressiva. Para os autores, é justamente o fenômeno da paralinguagem que sinaliza informações sobre atitudes, opiniões e emoções do falante em relação ao interlocutor ou ao tópico discursivo. Nesse sentido, investigamos, neste trabalho, as manifestações paralinguísticas recorrentes em conversas informais para demonstrarmos seu papel expressivo na linguagem falada. Para tanto, fizemos um levantamento de 450 ocorrências de elementos paralinguísticos no processo de transcrição de amostras de falas do Português Regional Paraense produzidas em situações reais de conversação. Pressupondo que essas realizações não-verbais são caracterizadas por variações prosódicas, nós as submetemos a uma análise fonética por meio do software PRAAT. A partir dessa análise, constatamos a contribuição de duas propriedades: a frequência fundamental (F0) e o tempo de emissão, para a manifestação expressiva dos elementos paralinguísticos no discurso falado. Além disso, identificamos também a silabação como uma propriedade comum às realizações sonoras focalizadas. Após o processo de análise, fizemos a descrição do uso e do funcionamento desses elementos nas conversas, bem como da contribuição deles para a manifestação da fala expressiva. Os resultados nos mostram que os elementos paralinguísticos, além de contribuírem para a fluência do discurso falado, desempenham a função de sinalizar compreensão, interesse e/ou atenção, gerenciar relações interpessoais e expressar emoções, atitudes e afeto.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

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.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Sistemas de reconhecimento e síntese de voz são constituídos por módulos que dependem da língua e, enquanto existem muitos recursos públicos para alguns idiomas (p.e. Inglês e Japonês), os recursos para Português Brasileiro (PB) ainda são escassos. Outro aspecto é que, para um grande número de tarefas, a taxa de erro dos sistemas de reconhecimento de voz atuais ainda é elevada, quando comparada à obtida por seres humanos. Assim, apesar do sucesso das cadeias escondidas de Markov (HMM), é necessária a pesquisa por novos métodos. Este trabalho tem como motivação esses dois fatos e se divide em duas partes. A primeira descreve o desenvolvimento de recursos e ferramentas livres para reconhecimento e síntese de voz em PB, consistindo de bases de dados de áudio e texto, um dicionário fonético, um conversor grafema-fone, um separador silábico e modelos acústico e de linguagem. Todos os recursos construídos encontram-se publicamente disponíveis e, junto com uma interface de programação proposta, têm sido usados para o desenvolvimento de várias novas aplicações em tempo-real, incluindo um módulo de reconhecimento de voz para a suíte de aplicativos para escritório OpenOffice.org. São apresentados testes de desempenho dos sistemas desenvolvidos. Os recursos aqui produzidos e disponibilizados facilitam a adoção da tecnologia de voz para PB por outros grupos de pesquisa, desenvolvedores e pela indústria. A segunda parte do trabalho apresenta um novo método para reavaliar (rescoring) o resultado do reconhecimento baseado em HMMs, o qual é organizado em uma estrutura de dados do tipo lattice. Mais especificamente, o sistema utiliza classificadores discriminativos que buscam diminuir a confusão entre pares de fones. Para cada um desses problemas binários, são usadas técnicas de seleção automática de parâmetros para escolher a representaçãao paramétrica mais adequada para o problema em questão.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

30.00% 30.00%

Publicador:

Resumo:

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)