Zugl.: Clausthal, Techn. Univ., Diss., 2005

Zugl.: Braunschweig, Techn. University, Diss., 2006.

Zugl.: München, Universiẗat der Bundeswehr, Diss., 2009.

Stuttgart, Univ., Diss., 2004.

Universiẗat, Diss., 1999--München.

Techn. Universiẗat, Diss., 2002--Chemnitz.

Techn. University, Diss., 2006--Darmstadt.

Voice comparison is one of the most frequently addressed terms in the context of forensic phonetics; however, so far experts have not been able to find a speech parameter which reliably discriminates between two speakers. Formant dynamics have brought promising results in this respect, therefore in our study using linear discriminant analysis (LDA) we tested the speaker-discriminatory potential of formant trajectories on real forensic recordings. The aim was firstly, to compare the results of LDA when formant frequencies or coefficients of quadratic and cubic fit are used as predictors and secondly, to compare the results when the analyzed classes are balanced or not regarding the number of objects. As for the predictors, all of the types demonstrated comparable classification rates, nevertheless, as LDA limits the number of predictors in relation to the class size, the quadratic fit appears to be the most efficient. Even though LDA was able to discriminate between different voices above chance, it cannot be recommended for forensic use. It delivered highly inconsistent results when the number of objects in the classes was changed; and more importantly, it significantly discriminates between objects of the same speaker. Key words: formant trajectories, voice comparison, LDA, Czech, forensic phonetics

In this thesis, we assume observing a pair of trajectories of two objects which could interact with one another and we want to propose a way to test their independence. We formulate basic point process definitions and discuss ways to describe trajectory data. We formulate the theory behind Monte Carlo tests and global envelope testing. In Chapter 2, we propose a parametric model to represent trajectories and derive Maximum Likelihood estimates of its model. We conclude the chapter by exploring the performance of these estimates. In Chapter 3, we propose test statistics used to test for independence using a nonparametric Monte Carlo test based on a random shift approach. We perform a simulation study to assess the performance of these statistics under various conditions and discuss the selection of fine-tuning parameters. Finally, in Chapter 4, we study real data provided by the Voyageurs Wolf Project and apply the proposed tests on real wolf trajectories. 1

Cílem práce je vytvoření přehledu o existujících přístupech pro předzpracování dopravních dat se zaměřením na objevování sémantických trajektorií a návrh a vývoj rámce, který integruje dopravní data z GPS senzorů se sémantikou. Problém analýzy nezpracovaných trajektorií spočíva v tom, že není natolik vyčerpávající, jako analýza trajektorií, které obsahují smysluplný kontext. Po nastudování různých přístupů a algoritmů sleduje návrh a vývoj rámce, který objevuje semantická místa pomocí schlukovací metody záložené na hustotě, aplikované na body zastavení v trajektoriích. Návrh a implementace rámce byl zhodnotěn na veřejně přístupných datových souborech obsahujících nezpracované GPS záznamy.