Externe Publikationen
Refine
Year of publication
- 2021 (21) (remove)
Document Type
Has Fulltext
- no (21)
Is part of the Bibliography
- no (21)
Keywords
- Aged (1)
- Aging (1)
- Brain Mapping (1)
- Brain/diagnostic imaging (1)
- COVID-19 (1)
- Chinese older adults (1)
- Communicable Disease Control (1)
- Crowdsourcing (1)
- Diffusion Tensor Imaging (1)
- Distributed intelligent home (1)
Institute
Begutachtungsstatus
- peer-reviewed (13)
Speech quality and likability is a multi-faceted phenomenon consisting of a combination of perceptory features that cannot easily be computed nor weighed automatically. Yet, it is often easy to decide which of two voices one likes better, even though it would be hard to describe why, or to name the underlying basic perceptory features. Although likability is inherently subjective and individual preferences differ, generalizations are useful and there is often a broad intersubjective consensus about whether one speaker is more likeable than another. We present a methodology to efficiently create a likability ranking for many speakers from crowdsourced pairwise likability ratings which focuses manual rating effort on pairs of similar quality using an active sampling technique. Using this methodology, we collected pairwise likability ratings for many speakers (>220) from many raters (>160). We analyze listener preferences by correlating the resulting ranking with various acoustic and prosodic features. We also present a neural network that is able to model the complexity of listener preferences and the underlying temporal evolution of features. The recurrent neural network achieves remarkably high performance in estimating the pairwise decisions and an ablation study points toward the criticality of modeling temporal aspects in speech quality assessment.
Dubbing, i.e., the lip-synchronous translation and revoicing of audio-visual media into a target language from a different source language, is essential for the full-fledged reception of foreign audio-visual media, be it movies, instructional videos or short social media clips. In this paper, we objectify influences on the ‘dubbability’ of translations, i.e., how well a translation would be synchronously revoiceable to the lips on screen. We explore the value of traditional heuristics used in evaluating the qualitative aspects, in particular matching bilabial consonants and the jaw opening while producing vowels, and control for quantity, i.e., that translations are similar to the source in length. We perform an ablation study using an adversarial neural classifier which is trained to differentiate “true” dubbing translations from machine translations. While we are able to confirm the value of matching lip closure in dubbing, we find that the opening angle of the jaw as determined by the realized vowel may be less relevant than frequently considered in audio-visual translation.
Guest Editorial Introduction to the Focused Section on Mechatronics and Automation for Constructions
(2021)
Rapid advances in modern technologies have completely revolutionized many industries in recent years. It is anticipated that mechatronic and automation technologies would play an important role in transforming the construction industry to embrace for the fourth industrial revolution. However, construction automation problems bring up new research challenges that diverge from traditional methods. Unlike the factory environment, which is typically structured and predictable, construction sites are dynamic places where the working environment is unstructured and always changing. Due to lack of skilled labor, time and cost overruns, quality deficiencies, and the recent pandemics, mechatronic and automation technologies offer solutions for future safe, rapid, performative, prize worthy, and digitally protocolled construction projects. The coexistence of human workers, heavy vehicles, varying environmental conditions, and automated mechatronic systems also make safe human–machine interaction an important issue. Beyond expertise in a specific discipline, construction automation also requires multidisciplinary expertise to integrate with various fields, such as Internet of Things (IOT), robotics and its construction oriented subsystems, adaptive/robust control, machine vision, sensing technologies, artificial intelligence (AI), and building/construction/process information modeling (BIM/CIM/PIM) for automated construction process management and design. The main aims of this focused section in the IEEE/ASME Transactions on Mechatronics (TMECH) are to document the current state of the art in mechatronics and automation for constructions, and to present new results in several emerging research areas.
In this paper, we present a study in which a robot initiates interactions with people passing by in an in-the-wild scenario. The robot adapts the loudness of its voice dynamically to the distance of the respective person approached, thus indicating who it is talking to. It furthermore tracks people based on information on body orientation and eye gaze and adapts the text produced based on people's distance autonomously. Our study shows that the adaptation of the loudness of its voice is perceived as personalization by the participants and that the likelihood that they stop by and interact with the robot increases when the robot incrementally adjusts its behavior.
Lebensdauerbemessung
(2021)
Christoph Gehlen, Till Felix Mayer, Charlotte Thiel und Christian Fischer beschreiben die Lebensdauerbemessung von Beton. Umfassend werden Transport‐ und Schädigungsmodelle vorgestellt, die die Mechanismen der Carbonatisierung, der Chlorideindringung, der Korrosion und der korrosionsinduzierten Rissbildung im Stahlbeton beschreiben. Die damit einhergehende Verbundthematik wird erläutert. Auch wird auf alle Mechanismen der Betonkorrosion eingegangen. Die Bemessung in Bezug auf die Dauerhaftigkeit und damit Abschätzungen für die Lebensdauer von Beton wird in drei unterschiedlich genauen Formaten geführt. Neben dem vollprobabilistischen Format wird beschrieben, wie Bemessungen auch auf Grundlage von Nachweisen basierend auf Teilsicherheitsbeiwerten durchgeführt werden können. Daran anschließend wird aufgezeigt, welche deskriptiven Bemessungsansätze sich daraus ableiten lassen. An einigen exemplarisch herausgegriffenen Objektbeispielen wird die Lebensdauerbemessung konkret vorgeführt.
We present an open source plugin for live subtitling in the popular open source video conferencing software BigBlueBut-ton. Our plugin decodes each speaker’s audio stream separately and in parallel, thereby obliviating the need for speaker di-arization and seamlessly handling overlapped talk. Any Kaldi-compatible nnet3 model can be used with our plugin and we demonstrate it using freely available TDNN-HMM-based ASR models for English and German. Our subtitles can be used as they are (e.g., in loud environments) or can form the basis for further NLP processes. Our tool can also simplify the collection of remotely recorded multi-party dialogue corpora.
Single-task construction robots (STCRs) have become a popular research topic for decades. However, there is still a gap in the ubiquitous application of STCRs for onsite construction due to various reasons, such as cost concerns. Therefore, cost–benefit analysis (CBA) can be used to measure the net economic benefit of the STCRs, compared to traditional construction methods, in order to boost the implementation of STCRs. This paper presents a simple and practical framework for the economic evaluation of STCRs and conducts a case study of a cable-driven facade installation robot to verify the method. The results show that the cable-driven robot for facade installation is worth investing in in the UK, as well as in the majority of G20 countries. Furthermore, other socioenvironmental implications of STCRs and the limitations of the study are also discussed. In conclusion, the proposed method is highly adaptable and reproducible. Therefore, researchers, engineers, investors, and policy makers can easily follow and customize this method to assess the economic advantages of any STCR systems, compared to traditional construction technologies.
Population aging is one of the major challenges facing the world. In particular, the advent of China's aging society caused by various factors will be a major threat to its future development. Therefore, serious measures need to be taken to achieve its demographic sustainability. Smart furniture can be considered as a novel subcategory of gerontechnology. One of the main outcomes of the EU-funded REACH project was a variety of smart furniture named Personalized Intelligent Interior Units (PI2Us) which served as the key component of a distributed intelligent home to promote the health and activity level of older adults. This outcome can potentially be a solution to mitigate the consequences caused by population aging. In order to understand the attitudes and opinions of Chinese older adults towards the relevant technologies, the authors conducted an opinion survey using the PI2Us as an example, which sampled more than 380 older adults in 26 out of 34 provincial-level administrative divisions of China. The survey showed that Chinese older adults in general have a highly positive attitude towards smart furniture and smart home technologies. Several other insights also can be revealed from the survey. Based on further analyses, the paper summarized why the elderly-oriented smart furniture and distributed intelligent home has the potential to thrive in China's market soon. Finally, a three-year project action plan for implementing localized solutions in cooperation with a large Chinese furniture manufacturer was presented.
The SMOOTH-robot is a mobile robot that-due to its modularity-combines a relatively low price with the possibility to be used for a large variety of tasks in a wide range of domains. In this article, we demonstrate the potential of the SMOOTH-robot through three use cases, two of which were performed in elderly care homes. The robot is designed so that it can either make itself ready or be quickly changed by staff to perform different tasks. We carefully considered important design parameters such as the appearance, intended and unintended interactions with users, and the technical complexity, in order to achieve high acceptability and a sufficient degree of utilization of the robot. Three demonstrated use cases indicate that such a robot could contribute to an improved work environment, having the potential to free resources of care staff which could be allocated to actual care-giving tasks. Moreover, the SMOOTH-robot can be used in many other domains, as we will also exemplify in this article.