(in English): Voice disguise can potentially occur in every utterance that is associated with any criminal case. In order to identify the perpetrator it is necessary to analyze the speech and understand how the different types of voice disguise can affect the speaker's voice qualities. This thesis focuses on the ability of voice disguise, portraying three groups of speakers in relation to their educational background. The aim of this work is to determine the strategies adopted by the speaker to conceal his/her identity and furthermore it poses the question whether differences among the three groups of speakers, their choice of strategy and its inherent success can be found. The basis for this research stems from 86 recordings which were undertaken in Pilsen and Prague with 43 young people aged 20 to 31. Two read utterances, one undisguised and the other freely disguised, were obtained from each of the participants and were compared with each other. The results show that the preferred forms of voice disguise appeared to involve changes in phonation - especially decrease or increase of fundamental frequency of the speaker's voice. Among the three groups of speakers, their choice and the success of the chosen strategy only minor differences could be found, yet for a final confirmation of this...

AbstractAbstractAbstractAbstract This diploma thesis aims to contribute to the field of speaker recognition in the domain of temporal changes in the speech signal. After a brief introduction into forensic phonetics, it gives an outline of approaches and factors which help or hinder successful recognition. The focus is then shifted to the temporal structure of speech and approaches to its analysis currently in use. The practical section of this thesis consists of an experiment designed to assess the contribution of certain temporal measures to speaker recognition. The variables used here are %V (the proportion of vocalic intervals within a sentence), ΔV and ΔC (the standard deviation of the duration of vocalic/consonantal intervals within a sentence), VarcoV and VarcoC (the previous variables normalised for average interval duration) and the Pairwise Variability Indices, both vocalic and consonantal, raw and normalised. Beside these, another variable is used to capture the local articulation rate and especially final deceleration in the utterances - LAR (the inverse of the distance between successive midpoints of the vocalic intervals). Whereas the first mentioned variables are not very successful in distinguishing the speakers, LAR seems very well suited for capturing speaker idiosyncrasies, although...

A procedure is presented that is capable of extracting various speaker features, and is of particular value for analyzing records containing single words and shorter segments of speech. By taking advantage of the fast convergence properties of adaptive filtering, the approach is capable of modeling the nonstationarities due to both the vocal tract and vocal cord dynamics. Specifically, the procedure extracts the vocal tract estimate from within the closed glottis interval and uses it to obtain a time-domain glottal signal. This procedure is quite simple, requires minimal manual intervention (in cases of inadequate pitch detection), and is particularly unique because it derives both the vocal tract and glottal signal estimates directly from the time-varying filter coefficients rather than from the prediction error signal. Using this procedure, several glottal signals are derived from human and synthesized speech and are analyzed to demonstrate the glottal waveform modeling performance and kind of glottal characteristics obtained therewith. Finally, the procedure is evaluated using automatic speaker identity verification. / Ph. D.

Despite a continuous development in computer sciences and related disciplines, speaker identification remains one of the most challenging tasks in forensic phonetics. The reason for this is the fact that our knowledge of how identity is reflected in the acoustic signal is still limited. The present study aims to contribute to the search of speaker-specific cues by examining spectral properties of the source signal. Specifically, it examines to what extent three short-term measures of spectral tilt, namely H1-H2, H1-A1 and H1-A3, can discriminate 16 Czech female speakers. It also addresses the influence of vowel quality, syllable status with respect to stress and position of stress group in the utterance on the values of these measures. The results show that these parameters do have some discriminative power, though the contribution of individual parameters differs. The study indicates that discrimination of speakers is the most successful in stressed syllables and argues that individual vowels could differ in their usefulness for speaker identification. The results of LDA based on these short- term measures of spectral tilt were complemented with long-term measures, namely alpha index, Kitzing index and Hammarberg index which quantify the slope of the LTAS. The present study suggests that...

Wie sich die Sprachwahrnehmung an ständig eingehende Informationen anpasst, ist eine Schlüsselfrage in der Gedanken- und Gehirnforschung. Die vorliegende Dissertation zielt darauf ab, zum Verständnis von Anpassungen an die Sprecheridentität und Sprachfehler während der Sprachverarbeitung beizutragen und unser Wissen über die Rolle der kognitiven Kontrolle bei der Sprachverarbeitung zu erweitern. Zu diesem Zweck wurden ereigniskorrelierte Potentiale (EKPs, englisch: event-related potentials, ERPs) N400 und P600 in der Elektroenzephalographie (EEG) analysiert. Die vorliegende Arbeit befasste sich insbesondere mit der Frage nach der Anpassung an die Sprecheridentität bei der Verarbeitung von zwei Arten von Sprachfehlern (Xu, Abdel Rahman, & Sommer, 2019), und untersuchte die proaktive Anpassungen, die durch die Erkennung von Sprachfehlern (Xu, Abdel Rahman, & Sommer, 2021) und durch die Sprecher(dis)kontinuität über aufeinanderfolgende Sätze in Situationen mit mehreren Sprechern ausgelöst wurden (Xu, Abdel Rahman, & Sommer, 2021, in press). Die Ergebnisse zeigten, dass unterschiedliche Sprachverarbeitungsstrategien entsprechend der Sprecheridentität von Muttersprachlern oder Nicht-Muttersprachlern und zwei verschiedenen Arten von Sprachfehlern angepasst wurden, was sich in unterschiedlichen N400- und P600-Effekten widerspiegelte. Darüber hinaus kann die Erkennung von Konflikten (Sprachfehler) und Sprecher(dis)kontinuität über aufeinanderfolgende Sätze hinweg eine proaktive kognitive Kontrolle erfordern, die die Verarbeitungsstrategien für den folgenden Satz schnell anpasst, was sich in bisher nicht gemeldeten sequentiellen Anpassungseffekten in der P600-Amplitude manifestierte. Basierend auf dem DMC Modell (Braver, 2012; Braver, Gray, & Burgess, 2007) und dem Überwachungsmodell der Sprachverarbeitung (van de Meerendonk, Indefrey, Chwilla, & Kolk, 2011) schlage ich vor, dass die P600-Amplitude nicht nur reaktive Anpassungen manifestiert, die durch Konflikterkennung ausgelöst werden, nämlich die klassischen P600-Effekte, die eine erneute Analyse der Sprachverarbeitung widerspiegeln, sondern auch proaktive Anpassungen in der Überwachung der Sprachverarbeitung, die Mechanismen der kognitiven Kontrolle von Aufmerksamkeit und Gedächtnis beinhalten. / How language perception adapts to constantly incoming information is a key question in mind and brain research. This doctoral thesis aims to contribute to the understanding of adaptation to speaker identity and speech error during speech processing, and to enhance our knowledge about the role of cognitive control in speech processing. For this purpose, event-related brain potentials (ERPs) N400 and P600 in the electroencephalography (EEG) were analyzed. Specifically, the present work addressed the question about adaptation to the speaker’s identity in processing two types of speech errors (Xu, Abdel Rahman, & Sommer, 2019), and explored proactive adaptation initiated by the detection of speech errors (Xu, Abdel Rahman, & Sommer, 2021) and by speaker (dis-)continuity across consecutive sentences in multi-speaker situations (Xu, Abdel Rahman, & Sommer, 2021, in press). Results showed that different speech processing strategies were adapted according to native or non-native speaker identity and two different types of speech errors, reflected in different N400 and P600 effects. In addition, detection of conflict (speech error) and speaker (dis-)continuity across consecutive sentences engage cognitive control to rapidly adapt processing strategies for the following sentence, manifested in hitherto unreported sequential adaptation effects in the P600 amplitude. Based on the DMC model (Braver, 2012; Braver, Gray, & Burgess, 2007) and the monitoring theory of language perception (van de Meerendonk, Indefrey, Chwilla, & Kolk, 2011), I propose that the P600 amplitude manifests not only reactive adaptations triggered by conflict detection, i.e., the classic P600 effect, reflecting reanalysis of speech processing, but also proactive adaptations in monitoring the speech processing, engaging cognitive control mechanisms of attention and memory.