Quality and Usability Lab

18 Items

Recent Submissions
NISQA Speech Quality Corpus

Mittag, Gabriel (2021-04)

The NISQA Speech Quality Corpus contains two training, two validation and four test datasets that have been used for training and evaluating the deep learning based speech quality model NISQA. Overall, it contains more than 14,000 speech files with annotated speech quality and speech quality dimension ratings.

DNC: Dataset for Noise Classification

Rafael, Zequeira Jiménez (2021)

The DNC dataset contains 4377 environmental background noise recordings labeled according to the type of noise. The recordings are approximately equally balanced between three main categories, i.e., *"mechanic"*, *"melodic"*, and *"quiet"*. These noise categories were selected as we found in a previous study that these are the background noises that can distract users in crowdsourcing when perf...

NDNetGaming - development of a no-reference deep CNN for gaming video quality prediction

Utke, Markus ; Zadtootaghaj, Saman ; Schmidt, Steven ; Bosse, Sebastian ; Möller, Sebastian (2020-07-24)

Gaming video streaming services are growing rapidly due to new services such as passive video streaming of gaming content, e.g. Twitch.tv, as well as cloud gaming, e.g. Nvidia GeForce NOW and Google Stadia. In contrast to traditional video content, gaming content has special characteristics such as extremely high and special motion patterns, synthetic content and repetitive content, which poses...

DNLE: Dataset for Noise Level Estimation

Rafael, Zequeira Jiménez (2021)

The DNLE dataset contains 1668 environmental background noise recordings labeled according to type and level of noise. The recordings are approximately equally balanced between three main categories, i.e., "mechanic", "melodic", and "quiet". These noise categories were selected as we found in a previous study that these are the background noises that can distract users in crowdsourcing when per...

Human processing of transmitted speech varying in perceived quality

Uhrig, Stefan Josef (2021)

The present thesis addresses human information processing of technologically transmitted speech, especially the effects of varying speech transmission quality (e.g. due to background noise or limitations in transmission bandwidth). The concept of “perceived quality” refers to an evaluative perceptual feature that integrates a subset of more descriptive perceptual features or “perceptual quality...

Towards speech quality assessment using a crowdsourcing approach: evaluation of standardized methods

Naderi, Babak ; Zequeira Jiménez, Rafael ; Hirth, Matthias ; Möller, Sebastian ; Metzger, Florian ; Hoßfeld, Tobias (2020-11-22)

Subjective speech quality assessment has traditionally been carried out in laboratory environments under controlled conditions. With the advent of crowdsourcing platforms tasks, which need human intelligence, can be resolved by crowd workers over the Internet. Crowdsourcing also offers a new paradigm for speech quality assessment, promising higher ecological validity of the quality judgments at...

Neural sequential transfer learning for relation extraction

Alt, Christoph Benedikt (2021)

Relation extraction (RE) is concerned with developing methods and models that automatically detect and retrieve relational information from unstructured data. It is crucial to information extraction (IE) applications that aim to leverage the vast amount of knowledge contained in unstructured natural language text, for example, in web pages, online news, and social media; and simultaneously requ...

How Do Induced Affective States Bias Emotional Contagion to Faces? A Three-Dimensional Model

Pinilla, Andrés ; Tamayo, Ricardo M. ; Neira, Jorge (2020-01-31)

Affective states can propagate in a group of people and influence their ability to judge others’ affective states. In the present paper, we present a simple mathematical model to describe this process in a three-dimensional affective space. We obtained data from 67 participants randomly assigned to two experimental groups. Participants watched either an upsetting or uplifting video previously c...

Konzeption eines MOOC der TU9 zum Thema Communication Acoustics

Möller, Sebastian ; Ahrens, Jens ; Altinsoy, Ercan ; Fels, Janina ; Müller, Gerhard ; Reimers, Gabriel ; Seeber, Bernhard ; Vorländer, Michael ; Weinzierl, Stefan (2016)


Psychological needs as motivators for security and privacy actions on smartphones

Kraus, Lydia ; Wechsung, Ina ; Möller, Sebastian (2017-06)

Much work has been conducted to investigate the obstacles that keep users from using mitigations against security and privacy threats on smartphones. By contrast, we conducted in-depth interviews (N = 19) to explore users’ motivations for voluntarily applying security and privacy actions on smartphones. Our work focuses on analyzing intrinsic motivation in terms of psychological need fulfillmen...

Object-based audio reproduction and the audio scene description format

Geier, Matthias ; Ahrens, Jens ; Spors, Sascha (2010)

The introduction of new techniques for audio reproduction such as HRTF-based technology, wave field synthesis and higher-order Ambisonics is accompanied by a paradigm shift from channel-based to object-based transmission and storage of spatial audio. Not only is the separate coding of source signal and source location more efficient considering the number of channels used for reproduction by la...

Evaluating embodied conversational agents in multimodal interfaces

Weiss, Benjamin ; Wechsung, Ina ; Kühnel, Christine ; Möller, Sebastian (2015)

Based on cross-disciplinary approaches to Embodied Conversational Agents, evaluation methods for such human-computer interfaces are structured and presented. An introductory systematisation of evaluation topics from a conversational perspective is followed by an explanation of social-psychological phenomena studied in interaction with Embodied Conversational Agents, and how these can be used fo...

Gesture-based user authentication on mobile devices using accelerometer and gyroscope

Guse, Dennis (2017)

Mobile devices offer their users lots of possibilities and a feeling of freedom. However, this freedom comes along with new security threats. Sensitive data might be stolen and abused, if an unauthorized person gets unrestricted access to such devices. Therefore, user authentication mechanisms are required. So far authentication mechanisms like PINs and passwords do not take into account the li...

Matlab Scripts for the Book "Analytic Methods of Sound Field Synthesis"

Ahrens, Jens (2012-06-01)

The present Matlab scripts accompany the book "Analytic Methods of Sound Field Synthesis" by Jens Ahrens. Usage instructions can be found here: http://www.soundfieldsynthesis.org/matlab/

The sum of two models: how a composite model explains unexpected user behavior in a dual-task scenario

Halbrügge, Marc ; Russwinkel, Nele (2016)

Maintaining cognitive control while pursuing several tasks at the same time is hard, especially when the current problem states of these tasks need to be represented in memory. We are investigating the mutual influence of a self-paced and a reactive task with regard to completion time and error rates. Against initial expectations, the interruptions from the reactive task did not lead to more er...

Towards the evaluation of cognitive models using anytime intelligence tests

Halbrügge, Marc (2016)

Cognitive models are usually evaluated based on their fit to empirical data. Artificial intelligence (AI) systems on the other hand are mainly evaluated based on their performance. Within the field of artificial general intelligence (AGI) research, a new type of performance measure for AGI systems has recently been proposed that tries to cover both humans and artificial systems: Anytime Intelli...

ACT-R Model for Predicting Performance in the DSF Task

Halbrügge, Marc (2009-07-25)

Dynamic Stock Flow (DSF) problems are a well-established paradigm for research on human decision making under uncertainty. This cognitive model implements a theoretic account on how humans solve DSF problems using the cognitive architecture ACT-R.

Simulation des Interaktionsverhaltens von Senioren bei der Benutzung von mobilen Endgeräten

Schulz, Matthias (2016)

Das Ziel dieser Arbeit ist es, eine bestehende Software zur Automatischen Usability Evaluierung (AUE) dahingehend zu erweitern, dass demografische Verteilungen über Einschränkungen in der älteren Bevölkerung in den Simulationsprozess einfließen und Auswirkungen von fehlenden oder unpassenden mentalen Modellen des Eingabegerätes simuliert werden können. Die vorliegende Arbeit dokumentiert den ak...