Global ETD Search

1	Investigation into automatic speech recognition of different dialects of Northern Sotho Mapeka, Madimetja Asaph January 2005 (has links) Thesis (MSc. (Computer Science)) -- University of Limpopo, 2005 / Refer to the document / Telkom (SA), HP (SA) and National Research Fund Automatic speech recognizer Speech technology Dialects Automatic speech recognition Speech perception
2	Creating a Graph Database from a Set of Documents / Skapandet av en grafdatabas från ett set av dokument Nikolic, Vladan January 2015 (has links) In the context of search, it may be advantageous in some use-cases to have documents saved in a graph database rather than a document-orientated database. Graph databases are able to model relationships between objects, in this case documents, in ways which allow for efficient retrieval, as well as search queries that are slightly more specific or complex. This report will attempt to explore the possibilities of storing an existing set of documents into a graph database. A Named Entity Recognizer was used on a set of news articles in order to extract entities from each news article’s body of text. News articles that contain the same entities are then connected to each other in the graph. Ideas to improve this entity extraction are also explored. The method of evaluation that was utilized in this report proved not to be ideal for this task in that only a relative measure was given, not an absolute one. As such, no absolute answer with regards to the quality of the method can be presented. It is clear that improvements can be made, and the result should be subject to further study. / I ett sökkontext kan det vara födelaktigt att i några användarscenarion utgå från dokument lagrade i en grafdatabas gentemot en dokument-orienterad databas. Grafdatabaser kan modellera förhållanden mellan objekt, som i detta fall är dokument, på ett sätt som ökar effektiviteten för vissa mer specifika eller komplexa sökfrågor. Denna rapport utforskar möjligheterna i att lagra existerande dokument i en grafdatabas. En Named Entity Recognizer används för att extrahera entiter från en stor samling nyhetsartiklar. Nyhetsartiklar som innehåller samma entiteter är sedan kopplade till varandra i grafen. Dessutom undersöks möjligheter till att förbättra extraheringen av entiteter. Evalueringsmetoden som användes visade sig mindre än ideal, då endast en relativ snarare än absolut bedömning kan göras av den slutgiltiga grafen. Därav kan inget slutgiltigt svar ges angående grafens och metodens kvalitet, men resultatet bör vara av intresse för framtida undersökningar. graph database documents NER named entity recognition named entity recognizer relations Computer Sciences Datavetenskap (datalogi)
3	Aktuelle Herausforderungen der Kriminalistik: Qualifikationsarbeiten aus dem Studium der Polizei- und Sicherheitsforschung Berthel, Ralph 21 June 2023 (has links) Qualifikationsarbeiten im Bereich der Kriminalistik bewegen sich im Spannungsfeld von wissenschaftlichen Qualitätsansprüchen und (kriminal-)polizeilicher Praxisorientierung. Dass sich beides keinesfalls ausschließen muss, stellen die in diesem Band publizierten Masterarbeiten unter Beweis. Durchweg mit dem Prädikat „sehr gut“ bewertet, leisten sie beachtenswerte Beiträge zur Fortentwicklung der Kriminalistik als Wissenschaftsdisziplin sowie zu deren Theorie-Praxis-Transfer. Zugleich verdeutlichen sie die Vielfalt sowie die Komplexität der Herausforderungen, denen sich die Kriminalwissenschaften einerseits und die Sicherheitsakteure andererseits aktuell und künftig gegenübersehen. Konkret widmen sich die Arbeiten den folgenden Themen: •Der Gewalt auf der Spur – Schemabasierte Einbeziehung der Rechtsmedizin in das polizeiliche Ermittlungsverfahren bei Gewaltkriminalität gegen lebende Opfer •Wissenschaftliche Untersuchung humaner Exkremente zur Generierung einer effizienten Spurensicherungsmethode sowie Spurenauswertung •Einführung von „Super Recognizern“ in der Polizei Brandenburg – Eine Kosten-Nutzen-Analyse •Der Verdeckte Ermittler – Analyse kriminaltaktischer Anpassungserfordernisse info:eu-repo/classification/ddc/000 ddc:000
4	Voice Transformation And Development Of Related Speech Analysis Tools For Turkish Salor, Ozgul 01 January 2005 (has links) (PDF) In this dissertation, new approaches in the design of a voice transformation (VT) system for Turkish are proposed. Objectives in this thesis are two-fold. The first objective is to develop standard speech corpora and segmentation tools for Turkish speech research. The second objective is to consider new approaches for VT. A triphone-balanced set of 2462 Turkish sentences is prepared for analysis. An audio corpus of 100 speakers, each uttering 40 sentences out of the 2462-sentence set, is used to train a speech recognition system designed for English. This system is ported to Turkish to obtain a phonetic aligner and a phoneme recognizer. The triphone-balanced sentence set and the phonetic aligner are used to develop a speech corpus for VT. A new voice transformation approach based on Mixed Excitation Linear Prediction (MELP) speech coding framework is proposed. Multi-stage vector quantization of MELP is used to obtain speaker-specific line-spectral frequency (LSF) codebooks for source and target speakers. Histograms mapping the LSF spaces of source and target speakers are used for transformation in the baseline system. The baseline system is improved by a dynamic programming approach to estimate the target LSFs. As a second approach to the VT problem, quantizing the LSFs using k-means clustering algorithm is applied with dimension reduction of LSFs using principle component analysis. This approach provides speaker-specific codebooks out of the speech corpus instead of using MELP&#039 / s pre-trained LSF codebook. Evaluations show that both dimension reduction and dynamic programming improve the transformation performance.
5	Robust Detection, Visualization, Recognition, and Analysis of Cytoskeletal Structures in Fibrillar Scaffolds from 3-Dimensional Confocal Images Park, Do young January 2017 (has links) No description available. Computer Science Biomedical Engineering
6	Funções recursivas primitivas: caracterização e alguns resultados para esta classe de funções Gomes, Victor pereira 21 June 2016 (has links) Submitted by Maike Costa (maiksebas@gmail.com) on 2016-08-10T14:17:41Z No. of bitstreams: 1 arquivo total.pdf: 975005 bytes, checksum: 6f8194b9c0cb9c0bbd07b1d2b0ba4b9e (MD5) / Made available in DSpace on 2016-08-10T14:17:41Z (GMT). No. of bitstreams: 1 arquivo total.pdf: 975005 bytes, checksum: 6f8194b9c0cb9c0bbd07b1d2b0ba4b9e (MD5) Previous issue date: 2016-06-21 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / The class of primitive recursive functions is not a formal version to the class of algorithmic functions, we study this special class of numerical functions due to the fact of that many of the functions known as algorithmic are primitive recursive. The approach on the class of primitive recursive functions aims to explore this special class of functions and from that, present solutions for the following problems: (1) given the class of primitive recursive derivations, is there an algorithm, that is, a mechanical procedure for recognizing primitive recursive derivations? (2) Is there a universal function for the class of primitive recursive functions? If so, is this function primitive recursive? (3) Are all the algorithmic functions primitive recursive? To provide solutions to these issues, we base on the hypothetical-deductive method and argue based on the works of Davis (1982), Mendelson (2009), Dias e Weber (2010), Rogers (1987), Soare (1987), Cooper (2004), among others. We present the theory of Turing machines which is a formal version to the intuitive notion of algorithm, and after that the famous Church-Turing tesis which identifies the class of algorithmic functions with the class of Turing-computable functions. We display the class of primitive recursive functions and show that it is a subclass of Turing-computable functions. Having explored the class of primitive recursive functions we proved as results that there is a recognizer algorithm to the class of primitive recursive derivations; that there is a universal function to the class of primitive recursive functions which does not belong to this class; and that not every algorithmic function is primitive recursive. / A classe das funções recursivas primitivas não constitui uma versão formal para a classe das funções algorítmicas, estudamos esta classe especial de funções numéricas devido ao fato de que muitas das funções conhecidas como algorítmicas são recursivas primitivas. A abordagem acerca da classe das funções recursivas primitivas tem como objetivo explorar esta classe especial de funções e, a partir disto, apresentar soluções para os seguintes problemas: (1) dada a classe das derivações recursivas primitivas, há um algoritmo, ou seja, um procedimento mecânico, para reconhecer derivações recursivas primitivas? (2) Existe uma função universal para a classe das funções recursivas primitivas? Se sim, essa função é recursiva primitiva? (3) Toda função algorítmica é recursiva primitiva? Para apresentar soluções para estas questões, nos pautamos no método hipotético-dedutivo e argumentamos com base nos manuais de Davis (1982), Mendelson (2009), Dias e Weber (2010), Rogers (1987), Soare (1987), Cooper (2004), entre outros. Apresentamos a teoria das máquinas de Turing, que constitui uma versão formal para a noção intuitiva de algoritmo, e, em seguida, a famosa tese de Church-Turing, a qual identifica a classe das funções algorítmicas com a classe das funções Turing-computáveis. Exibimos a classe das funções recursivas primitivas, e mostramos que a mesma constitui uma subclasse das funções Turing-computáveis. Tendo explorado a classe das funções recursivas primitivas, como resultados, provamos que existe um algoritmo reconhecedor para a classe das derivações recursivas primitivas; que existe uma função universal para a classe das funções recursivas primitivas a qual não pertence a esta classe; e que nem toda função algorítmica é recursiva primitiva. Funções algorítmicas Funções recursivas primitivas Algoritmo reconhecedor Função universal Primitive recursive functions Recognizer algorithm Universal function Algorithmic functions CIENCIAS HUMANAS::FILOSOFIA
7	Rozpoznáváni standardních PILOT-CONTROLLER řídicích povelů v hlasové podobě / Voice recognition of standard PILOT-CONTROLLER control commands Kufa, Tomáš January 2009 (has links) The subject of this graduation thesis is an application of speech recognition into ATC commands. The selection of methods and approaches to automatic recognition of ATC commands rises from detailed air traffic studies. By the reason that there is not any definite solution in such extensive field like speech recognition, this diploma work is focused just on speech recognizer based on comparison with templates (DTW). This recognizor is in this thesis realized and compared with freely accessible HTK system from Cambrige University based on statistic methods making use of Hidden Markov models. The usage propriety of both methods is verified by practical testing and results evaluation.
8	Enhanching the Human-Team Awareness of a Robot Wåhlin, Peter January 2012 (has links) The use of autonomous robots in our society is increasing every day and a robot is no longer seen as a tool but as a team member. The robots are now working side by side with us and provide assistance during dangerous operations where humans otherwise are at risk. This development has in turn increased the need of robots with more human-awareness. Therefore, this master thesis aims at contributing to the enhancement of human-aware robotics. Specifically, we are investigating the possibilities of equipping autonomous robots with the capability of assessing and detecting activities in human teams. This capability could, for instance, be used in the robot's reasoning and planning components to create better plans that ultimately would result in improved human-robot teamwork performance. we propose to improve existing teamwork activity recognizers by adding intangible features, such as stress, motivation and focus, originating from human behavior models. Hidden markov models have earlier been proven very efficient for activity recognition and have therefore been utilized in this work as a method for classification of behaviors. In order for a robot to provide effective assistance to a human team it must not only consider spatio-temporal parameters for team members but also the psychological.To assess psychological parameters this master thesis suggests to use the body signals of team members. Body signals such as heart rate and skin conductance. Combined with the body signals we investigate the possibility of using System Dynamics models to interpret the current psychological states of the human team members, thus enhancing the human-awareness of a robot. / Användningen av autonoma robotar i vårt samhälle ökar varje dag och en robot ses inte längre som ett verktyg utan som en gruppmedlem. Robotarna arbetar nu sida vid sida med oss och ger oss stöd under farliga arbeten där människor annars är utsatta för risker. Denna utveckling har i sin tur ökat behovet av robotar med mer människo-medvetenhet. Därför är målet med detta examensarbete att bidra till en stärkt människo-medvetenhet hos robotar. Specifikt undersöker vi möjligheterna att utrusta autonoma robotar med förmågan att bedöma och upptäcka olika beteenden hos mänskliga lag. Denna förmåga skulle till exempel kunna användas i robotens resonemang och planering för att ta beslut och i sin tur förbättra samarbetet mellan människa och robot. Vi föreslår att förbättra befintliga aktivitetsidentifierare genom att tillföra förmågan att tolka immateriella beteenden hos människan, såsom stress, motivation och fokus. Att kunna urskilja lagaktiviteter inom ett mänskligt lag är grundläggande för en robot som ska vara till stöd för laget. Dolda markovmodeller har tidigare visat sig vara mycket effektiva för just aktivitetsidentifiering och har därför använts i detta arbete. För att en robot ska kunna ha möjlighet att ge ett effektivt stöd till ett mänskligtlag måste den inte bara ta hänsyn till rumsliga parametrar hos lagmedlemmarna utan även de psykologiska. För att tyda psykologiska parametrar hos människor förespråkar denna masteravhandling utnyttjandet av mänskliga kroppssignaler. Signaler så som hjärtfrekvens och hudkonduktans. Kombinerat med kroppenssignalerar påvisar vi möjligheten att använda systemdynamiksmodeller för att tolka immateriella beteenden, vilket i sin tur kan stärka människo-medvetenheten hos en robot. / <p>The thesis work was conducted in Stockholm, Kista at the department of Informatics and Aero System at Swedish Defence Research Agency.</p> robotics Artificial Intelligence AI System Dynamics Wireless Body Area Network WBAN sensors Psychology physiology human behavior Human-Robot-Interaction HRI robot Human-Team awareness human-robot RapidMiner Vensim JaHMM hidden markov models HMM eclipse rcp ARFF recognizer classification cross-validation human behavior stress detection Galvanic Skin Response Heart Rate Skin Temperature Finger Temperature Electrocardiogram ECG GSR ST Pupil Diameter PD Patient monitoring GPS Data acquisition dataset data set MODERE Yerkes-Dodson SD model SD Confusion matrix spatial MOUT Java Agent robotic agent Machine Learning activity recognition team oriented robot Evaluation Decoding Learning Forward Algorithm Backward Algorithm Baum-Welch feedback loop Situation Awareness SA Shared Mental Models SMM

Search results