The purpose of this project is to examine the extent to which sign language can be used as a means of communicating the text for hearing audiences attending classical vocal recitals. The project discusses historical practices for providing text translation of classical repertoire sung in foreign languages and gives an account of the increasing popularity of sign language interpretation for hearing audiences within the contemporary, commercial music industry. A trial performance is undertaken in order to examine the effectiveness of the idea in the context of classical vocal music. Feedback is gathered from the audience and singer’s perspective during performance and through observations made by studying the video documenting the performance. / <p>The sounding part of the work consists of the following recording: NJones100619. The Corona virus situation spring semester 2020 has caused limitations in the recording possibilities. The recording may be supplemented. </p>

Research into parsing sign language corpora is ongoing. Corpora for German Sign Language and Italian Sign Language have been parsed (Bungeroth et al., 2006; Mazzei, 2011, 2012, respectively). However, research into parsing a corpus of American Sign Language is non-existent. Examples of parsed ASL sentences in literature are typically isolated examples used to show a particular type of construction. Apparently no attempt has been made to parse an entire corpus of American Sign Language utterances. This thesis presents a method for constructing a grammar so that a parser implementing Combinatory Categorial Grammar can parse a corpus of American Sign Language. The results are evaluated and presented.

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / In peruvian sign language (PSL), recognition of static gestures has been proposed earlier. However, to state a conversation using sign language, it is also necessary to employ dynamic gestures. We propose a method to extract a feature vector for dynamic gestures of PSL. We collect a dataset with 288 video sequences of words related to dynamic gestures and we state a workflow to process the keypoints of the hands, obtaining a feature vector for each video sequence with the support of a video summarization technique. We employ 9 neural networks to test the method, achieving an average accuracy ranging from 80% and 90%, using 10 fold cross-validation.

The diploma thesis is focused on handling complaints in organizations providing social services. The process of handling complaints is conceived in the work as a process which, if properly set up and coordinated within the organization, can be useful in improving the services provided. The thesis summarizes professional theoretical knowledge in the field of complaint handling, describes the Czech legislative anchoring of work with complaints and offers an overview of possible processes procedures, rules and practices that can be used in practice. The practical part of the work is focused primarily on handling complaints in the field of providing interpretation of Czech sign language. Part of the diploma thesis is qualitative research, in which the process of handling complaints in the selected organization is diagnosed in detail. The results of the research include suggestions for possible procedures and recommendations that can help the organization streamline the complaint handling proces and can also be an inspiration for organizations that are open to a critical approach to their own complaint handling and possible implementation of changes.

Syftet med studien är att studera hur lärare introducerar och arbetar med likhetstecknet för att inkludera alla elever och ge dem förutsättningar i sin undervisning. Studiens urval är fyra verksamma lärare som genom semistrukturerade kvalitativa intervjuer belyser sina tankar, erfarenheter och åsikter om hur de arbetar och introducerar likhetstecknet, samt vilka svårigheter som kan uppstå. Resultatet visar att lärarna i studien har ett entydigt arbetssätt men att det finns faktorer som skiljer sig åt. Att det finns faktorer som skiljer sig åt tydliggörs genom att lärarna introducerar likhetstecknet med bland annat konkret material medan introduktionen av likhetstecknet kan se olika ut, lärarna använder olika arbetsmetoder där en lärare väljer att introducera addition och talkamrater innan likhetstecknet, medan en annan lärare uttrycker att likhetstecknet bör introduceras först. Studiens problem är att forskning och myndigheter visar på att elever missuppfattar likhetstecknets betydelse. Den slutsats vi kan dra utifrån syfte, problem och resultat är att lärare behöver anpassa undervisningen för att ge eleverna goda kunskaper för att kunna bemästra matematiken. / The purpose of the study is to observe how teachers introduce and work with an equal sign in order to include all students. This is to give them the prerequisites in their teaching. The study sample involves four active teachers who, through semi-structured qualitative interviews, shed light on their thoughts, experiences, and opinions on how teachers work and introduce the sign of equality as well as what difficulties may arise. The results show that the teachers involved in the study have an unambiguous way of working, however, there are factors that differ. This is shown by the teachers introducing the equals sign with, among other things, concrete material while the introduction of the equals sign can look different. The teachers use different working methods where one teacher chooses to introduce additions and speech mates before the equal sign, while another teacher expresses that the equal sign should be introduced first. The problem with the study is that the research and authorities show that students misunderstand the meaning of the equal sign. The conclusion we can draw based on purpose, problems, and results is that teachers need to adapt the teaching to give students sufficient knowledge to be able to master mathematics.

Masters of Science / Much work has been done in building systems that can recognise gestures, e.g. as a component of sign language recognition systems. These systems typically use whole gestures as the smallest unit for recognition. Although high recognition rates have been reported, these systems do not scale well and are computationally intensive. The reason why these systems generally scale poorly is that they recognize gestures by building individual models for each separate gesture; as the number of gestures grows, so does the required number of models. Beyond a certain threshold number of gestures to be recognized, this approach becomes infeasible. This work proposes that similarly good recognition rates can be achieved by building models for subcomponents of whole gestures, so-called cheremes. Instead of building models for entire gestures, we build models for cheremes and recognize gestures as sequences of such cheremes. The assumption is that many gestures share cheremes and that the number of cheremes necessary to describe gestures is much smaller than the number of gestures. This small number of cheremes then makes it possible to recognize a large number of gestures with a small number of chereme models. This approach is akin to phoneme-based speech recognition systems where utterances are recognized as phonemes which in turn are combined into words. We attempt to recognise and classify cheremes found in South African Sign Language (SASL). We introduce a method for the automatic discovery of cheremes in dynamic signs. We design, train and use hidden Markov models (HMMs) for chereme recognition. Our results show that this approach is feasible in that it not only scales well, but it also generalizes well. We are able to recognize cheremes in signs that were not used for training HMMs; this generalization ability is a basic necessity for chemere-based gesture recognition. Our approach can thus lay the foundation for building a SASL dynamic gesture recognition system.

Pavlovian conditioned stimuli can acquire incentive motivational properties, and this phenomenon can be measured in animals using Pavlovian conditioned approach behavior. Drugs of abuse can influence the expression of this behavior, and nicotine in particular exhibits incentive amplifying effects. Both conditioned approach behavior and drug abuse rely on overlapping corticolimbic circuitry. We hypothesize that the orbitofrontal cortex (OFC) regulates conditioned approach, and that one site of nicotine action is in the OFC where it reduces cortical output. To test this, we repeatedly exposed rats to 0.4 mg/kg nicotine (s.c.) during training and then pharmacologically inactivated the lateral OFC or performed in vivo electrophysiological recordings of lateral OFC neurons in the presence or absence of nicotine. In Experiment 1, animals were trained in a Pavlovian conditioning paradigm and behavior was evaluated after inactivation of the OFC by microinfusion of the GABA agonists baclofen and muscimol. In Experiment 2, we monitored phasic firing of OFC neurons during Pavlovian conditioning sessions. Nicotine reliably enhanced conditioned responding to the conditioned cue, and inactivation of the OFC reduced conditioned responding, especially the sign-tracking response. OFC neurons exhibited phasic excitations to cue presentation and during goal tracking, and nicotine acutely blunted this phasic neuronal firing. When nicotine was withheld, both conditioned responding and phasic firing in the OFC returned to the level of controls. These results suggest that the OFC is recruited for the expression of conditioned responses, and that nicotine acutely influences this behavior by reducing phasic firing in the OFC.

In the hearing-loss community, sign language is a primary tool to communicate with people while there is a communication gap between hearing-loss people with normal hearing people. Sign language is different from spoken language. It has its own vocabulary and grammar. Recent works concentrate on the sign language video caption which consists of sign language recognition and sign language translation. Continuous sign language recognition, which can bridge the communication gap, is a challenging task because of the weakly supervised ordered annotations where no frame-level label is provided. To overcome this problem, connectionist temporal classification (CTC) is the most widely used method. However, CTC learning could perform badly if the extracted features are not good. For better feature extraction, this thesis presents the novel self-attention-based fully-inception (SAFI) networks for vision-based end-to-end continuous sign language recognition. Considering the length of sign words differs from each other, we introduce the fully inception network with different receptive fields to extract dynamic clip-level features. To further boost the performance, the fully inception network with an auxiliary classifier is trained with aggregation cross entropy (ACE) loss. Then the encoder of self-attention networks as the global sequential feature extractor is used to model the clip-level features with CTC. The proposed model is optimized by jointly training with ACE on clip-level feature learning and CTC on global sequential feature learning in an end-to-end fashion. The best method in the baselines achieves 35.6% WER on the validation set and 34.5% WER on the test set. It employs a better decoding algorithm for generating pseudo labels to do the EM-like optimization to fine-tune the CNN module. In contrast, our approach focuses on the better feature extraction for end-to-end learning. To alleviate the overfitting on the limited dataset, we employ temporal elastic deformation to triple the real-world dataset RWTH- PHOENIX-Weather 2014. Experimental results on the real-world dataset RWTH- PHOENIX-Weather 2014 demonstrate the effectiveness of our approach which achieves 31.7% WER on the validation set and 31.2% WER on the test set. Even though sign language recognition can, to some extent, help bridge the communication gap, it is still organized in sign language grammar which is different from spoken language. Unlike sign language recognition that recognizes sign gestures, sign language translation (SLT) converts sign language to a target spoken language text which normal hearing people commonly use in their daily life. To achieve this goal, this thesis provides an effective sign language translation approach which gains state-of-the-art performance on the largest real-life German sign language translation database, RWTH-PHOENIX-Weather 2014T. Besides, a direct end-to-end sign language translation approach gives out promising results (an impressive gain from 9.94 to 13.75 BLEU and 9.58 to 14.07 BLEU on the validation set and test set) without intermediate recognition annotations. The comparative and promising experimental results show the feasibility of the direct end-to-end SLT

Facial and head movements have important linguistic roles in American Sign Language (ASL) and other sign languages and can often significantly alter the meaning or interpretation of what is being communicated. Technologies that enable accurate recognition of ASL linguistic markers could be a step toward greater independence and empowerment for the Deaf community. This study involved gathering over 2,000 photographs of five hearing subjects, five Deaf subjects, and five Child of Deaf Adults (CODA) subjects. Each subject produced the six universal emotional facial expressions: sad, happy, surprise, anger, fear, and disgust. In addition, each Deaf and CODA subject produced six different ASL linguistic facial expressions. A representative set of 750 photos was submitted to six different emotional facial expression recognition services, and the results were processed and compared across different facial expressions and subject groups (hearing, Deaf, CODA). Key observations from these results are presented. First, poor face detection rates are observed for Deaf subjects as compared to hearing and CODA subjects. Second, emotional facial expression recognition appears to be more accurate for Deaf and CODA subjects than for hearing subjects. Third, ASL linguistic markers, which are distinct from emotional expressions, are often misinterpreted as negative emotions by existing technologies. Possible implications of this misinterpretation are discussed, such as the problems that could arise for the Deaf community with increasing surveillance and use of automated facial analysis tools. Finally, an inclusive approach is suggested for incorporating ASL linguistic markers into existing facial expression recognition tools. Several considerations are given for constructing an unbiased database of the various ASL linguistic markers, including the types of subjects that should be photographed and the importance of including native ASL signers in the photo selection and classification process. / 2019-06-30T00:00:00Z

This thesis focuses on research of classifier verbs in Czech sign language. The aim of the thesis is to describe different types of classifier verbs in Czech sign language based on language material collected from deaf users of Czech sign language by means of the Verb of motion production. The thesis defines classifier verbs of motion, location, visual and geometric description, and handling and also describes various types of classifier handshapes that form them for a semantic perspective. Key words: verbs in Czech sign language, classifier, classifier verbs