Sistema de reconhecimento de fala tem amplo emprego no universo industrial, no aperfeiçoamento de operações e procedimentos humanos e no setor do entretenimento e recreação. O objetivo específico do trabalho foi conceber e desenvolver um sistema de reconhecimento de voz, capaz de identificar comandos de voz, independentemente do locutor. A finalidade precípua do sistema é controlar movimentos de robôs, com aplicações na indústria e no auxílio de deficientes físicos. Utilizou-se a abordagem da tomada de decisão por meio de uma rede neural treinada com as características distintivas do sinal de fala de 16 locutores. As amostras dos comandos foram coletadas segundo o critério de conveniência (em idade e sexo), a fim de garantir uma maior discriminação entre as características de voz, e assim alcançar a generalização da rede neural utilizada. O préprocessamento consistiu na determinação dos pontos extremos da locução do comando e na filtragem adaptativa de Wiener. Cada comando de fala foi segmentado em 200 janelas, com superposição de 25% . As features utilizadas foram a taxa de cruzamento de zeros, a energia de curto prazo e os coeficientes ceptrais na escala de frequência mel. Os dois primeiros coeficientes da codificação linear preditiva e o seu erro também foram testados. A rede neural empregada como classificador foi um perceptron multicamadas, treinado pelo algoritmo backpropagation. Várias experimentações foram realizadas para a escolha de limiares, valores práticos, features e configurações da rede neural. Os resultados foram considerados muito bons, alcançando uma taxa de acertos de 89,16%, sob as condições de pior caso da amostragem dos comandos. / Systems for speech recognition have widespread use in the industrial universe, in the improvement of human operations and procedures and in the area of entertainment and recreation. The specific objective of this study was to design and develop a voice recognition system, capable of identifying voice commands, regardless of the speaker. The main purpose of the system is to control movement of robots, with applications in industry and in aid of disabled people. We used the approach of decision making, by means of a neural network trained with the distinctive features of the speech of 16 speakers. The samples of the voice commands were collected under the criterion of convenience (age and sex), to ensure a greater discrimination between the voice characteristics and to reach the generalization of the neural network. Preprocessing consisted in the determination of the endpoints of each command signal and in the adaptive Wiener filtering. Each speech command was segmented into 200 windows with overlapping of 25%. The features used were the zero crossing rate, the short-term energy and the mel-frequency ceptral coefficients. The first two coefficients of the linear predictive coding and its error were also tested. The neural network classifier was a multilayer perceptron, trained by the backpropagation algorithm. Several experiments were performed for the choice of thresholds, practical values, features and neural network configurations. Results were considered very good, reaching an acceptance rate of 89,16%, under the `worst case conditions for the sampling of the commands.

This study proposes to examine the invented spelling patterns that Spanish speaking children create in their writing. Their writing samples were then transcribed and each word was categorized as either conventional or an invented spelling.

Pendant la perception de la parole, les locuteurs sont biaisés par un grand nombre de facteurs. Par exemple, il existe des limitations cognitives comme la mémoire ou l’attention, mais aussi des limitations linguistiques comme leur langue maternelle. Cette thèse se concentre sur deux de ces facteurs : les biais de traitement pendant la reconnaissance des mots, et les biais d’apprentissage pendant le processus de transmission. Ces facteurs peuvent se combiner et, au cours du temps, influencer l’évolution des langues. Dans la première partie de cette thèse, nous nous concentrons sur le processus de la reconnaissance des mots. Des recherches antérieures ont établi l’importance des traits phonologiques (p. ex. le voisement ou le lieu d’articulation) pendant le traitement de la parole. Cependant, nous en savons peu sur leur poids relatif les uns par rapport aux autres, et comment cela peut influencer la capacité des locuteurs à reconnaître les mots. Nous avons testé des locuteurs français sur leur capacité à reconnaître des mots mal prononcés et avons trouvé que les traits de mode et de lieu sont plus importants que le trait de voisement. Nous avons ensuite considéré deux sources de cette asymétrie et avons trouvé que les locuteurs sont biaisés et par la perception acoustique ascendante (les contrastes de mode sont plus facile à percevoir à cause de leur distance acoustique importante) et par la connaissance lexicale descendante (le trait de lieu est plus exploité dans le lexique français que les autres traits). Nous suggérons que ces deux sources de biais se combinent pour influencer les locuteurs lors de la reconnaissance des mots. Dans la seconde partie de cette thèse, nous nous concentrons sur la question d’un biais d’apprentissage. Il a été suggéré que les apprenants peuvent être biaisés vers l’apprentissage de certains patrons phonologiques grâce à leurs connaissances phonétiques. Cela peut alors expliquer pourquoi certains patrons sont récurrents dans la typologie, tandis que d’autres restent rares ou non-attestés. Plus spécifiquement, nous avons exploré le rôle d’un biais d’apprentissage sur l’acquisition de la règle typologiquement commune de l’harmonie vocalique comparée à celle de la règle non-attestée (mais logiquement équivalente) de la disharmonie vocalique. Nous avons trouvé des preuves d’un biais d’apprentissage aussi bien en perception qu’en production. En utilisant un modèle d’apprentissage itéré simulé, nous avons ensuite montré comment un biais, même petit, favorisant l’un des patrons, peut influencer la typologie linguistique au cours du temps et donc expliquer (en partie) la prépondérance de systèmes harmoniques. De plus, nous avons exploré le rôle du sommeil sur la consolidation mnésique. Nous avons montré que seul le patron commun bénéficie d’une consolidation et que cela est un facteur supplémentaire pouvant contribuer à l’asymétrie typologique. Dans l’ensemble, cette thèse considère certaines des sources de biais possibles chez l’individu et discute de comment ces influences peuvent, au cours du temps, faire évoluer les systèmes linguistiques. Nous avons démontré la nature dynamique et complexe du traitement de la parole, à la fois en perception et dans l’apprentissage. De futurs travaux devront explorer plus en détail comment ces différentes sources de biais sont pondérées les unes relativement aux autres. / During speech perception, listeners are biased by a great number of factors, including cognitive limitations such as memory and attention and linguistic limitations such as their native language. This thesis focuses on two of these factors: processing bias during word recognition, and learning bias during the transmission process. These factors are combinatorial and can, over time, affect the way languages evolve. In the first part of this thesis, we focus on the process of word recognition. Previous research has established the importance of phonological features (e.g., voicing or place of articulation) during speech processing, but little is known about their weight relative to one another, and how this influences listeners' ability to recognize words. We tested French participants on their ability to recognize mispronounced words and found that the manner and place features were more important than the voicing feature. We then explored two sources of this asymmetry and found that listeners were biased both by bottom-up acoustic perception (manner contrasts are easier to perceive because of their acoustic distance compared to the other features) and top-down lexical knowledge (the place feature is used more in the French lexicon than the other two features). We suggest that these two sources of bias coalesce during the word recognition process to influence listeners. In the second part of this thesis, we turn to the question of bias during the learning process. It has been suggested that language learners may be biased towards the learning of certain phonological patterns because of phonetic knowledge they have. This in turn can explain why certain patterns are recurrent in the typology while others remain rare or unattested. Specifically, we explored the role of learning bias on the acquisition of the typologically common rule of vowel harmony compared to the unattested (but logically equivalent) rule of vowel disharmony. We found that in both perception and production, there was evidence of a learning bias, and using a simulated iterated learning model, showed how even a small bias favoring one pattern over the other could influence the linguistic typology over time, thus explaining (in part) the prevalence of harmonic systems. We additionally explored the role of sleep on memory consolidation and showed evidence that the common pattern benefits from consolidation that the unattested pattern does not, a factor that may also contribute to the typological asymmetry. Overall, this thesis considers a few of the wide-ranging sources of bias in the individual and discusses how these influences can over time shape linguistic systems. We demonstrate the dynamic and complicated nature of speech processing (both in perception and learning) and open the door for future research to explore in finer detail just how these different sources of bias are weighted relative to one another.

<div>Cochlear implants (CI) are sensory neuroprostheses capable of partially restoring hearing loss by electrically stimulating the auditory nerve to mimic normal hearing conditions. Despite their success and ongoing advances in both hardware and software, CI patients can still struggle to understand speech, most notably in complex auditory settings, also referred to as the cocktail party problem. Efforts to develop new CI algorithms to overcome this challenge rely on CI simulators and vocoders to test with normal hearing (NH) patients. However, recent studies have suggested that these tools fail to reproduce the stimuli perceived by CI patients. It is therefore critical to develop tools capable of producing better representations of the stimuli as perceived by CI patients. Thus, this work proposes a framework that incorporates physiological models of the peripheral auditory nerve. Using these models, the framework generates stimulations that elicit a neural response at the auditory nerve closer to that observed in NH conditions. Stimulations generated by the framework were evaluated by performing a vowel identification task. However, the task was performed by a classifier trained using deep learning techniques instead of a CI patient. These results give insight into how the framework could be applied for the development and validation of CI stimulation strategies.</div>

This study compares, for listeners with normal hearing and listeners with hearing loss, the recognition performances obtained with digit-pair and digit-triplet stimulus sets presented in multitalker babble. Digits 1 through 10 (excluding 7) were mixed in approximately 1,000 ms segments of babble from 4 to -20 dB signal-to-babble (S/B) ratios, concatenated to form the pairs and triplets, and recorded on compact disc. Nine and eight digits were presented at each level for the digit-triplet and digit-pair paradigms, respectively. For the listeners with normal hearing and the listeners with hearing loss, the recognition performances were 3 dB and 1.2 dB better, respectively, on digit pairs than on digit triplets. For equal intelligibility, the listeners with hearing loss required an approximately 10 dB more favorable S/B than the listeners with normal hearing. The distributions of the 50% points for the two groups had no overlap.

No description available.

There are many more ways to automate the application process like using some commercial software’s that are used in big organizations to scan bills and forms, but this application is only for the static frames or formats. In our application, we are trying to automate the non-static frames as the study certificate we get are from different counties with different universities. Each and every university have there one format of certificates, so we try developing a very new application that can commonly work for all the frames or formats. As we observe many applicants are from same university which have a common format of the certificate, if we implement this type of tools, then we can analyze this sort of certificates in a simple way within very less time. To make this process more accurate we try implementing SVM and Clustering methods. With these methods we can accurately map courses in certificates to ASE study path if not to exclude list. A grade calculation is done for courses which are mapped to an ASE list by separating the data for both labs and courses in it. At the end, we try to award some points, which includes points from ASE related courses, work experience, specialization certificates and German language skills. Finally, these points are provided to the chair to select the applicant for master course ASE.

No description available.

The purpose of this study was to develop, digitally record, evaluate, and equate Cantonese trisyllabic words which could then be used in the measurement of the speech reception threshold. A selection of 90 frequently utilized trisyllabic words were selected and then digitally recorded by male and female talkers of Standard Cantonese and presented to 20 subjects with normal hearing beginning at 6 dB below their pure-tone average (PTA) and ascending in 2 dB increments until one of the following criteria had been met: (a) the participant responded correctly to 100% of the test items, or (b) the presentation level reached 16 dB HL. Using logistic regression, psychometric functions were calculated for each word. Twenty-eight trisyllabic words with the steepest psychometric function slopes were selected. The psychometric function slopes for the 28 selected words, at 50% threshold, ranged from 10.3 %/dB to 19.6 %/dB (M = 14.5 %/dB) for the male talker and from 10.3 %/dB to 22.7 %/dB (M = 14.9 %/dB) for the female talker. To decrease the variability among the words the intensities were digitally adjusted to match the mean subject PTA (4.5 dB HL). The resulting lists included mean slopes from 20 to 80% with of a range of 8.9 %/dB to 16.9 %/dB (M = 12.6 %/dB) for the male talker and a range of 8.9 %/dB to 19.7 %/dB (M = 12.9 %/dB) for the female talker. Digital recordings of the psychometrically equivalent trisyllabic words are available on compact disc.

Negative attitudes towards atheists are hardly a new trend in our society. However, given the pervasiveness of the prejudices and the lack of foundation for them, it seems warranted to explore the underlying elements of these attitudes. Identifying these constitutive elements may help pick apart the different contributing factors and perhaps mitigate or at least understand them in the future. The present study was designed to identify which myths or stereotypes about atheists are most influential in these attitudes. A Lexical Decision Task was utilized to identify which words related to popular stereotypes are most related to the label atheists. The labels Atheists, Christians, and Students were compared to positive words, negatives words, words or interests, neutral words, and non-word strings. Analyses revealed no significant differences among the participants' reaction times in these various comparisons, regardless of religion, level of belief in god, level of spirituality, or being acquainted with atheists. Possible explanations for these results are discussed in this thesis.