Information und Kommunikation
Refine
Year of publication
- 2014 (18) (remove)
Document Type
- conference proceeding (article) (11)
- Article (7)
Has Fulltext
- no (18)
Is part of the Bibliography
- no (18)
Keywords
- speech synthesis (3)
- Materials (2)
- Software (2)
- Software engineering (2)
- incremental processing (2)
- simultaneous interpreting (2)
- 3G (1)
- 4G (1)
- Accuracy (1)
- Activating Learning (1)
Institute
Begutachtungsstatus
- peer-reviewed (15)
This paper describes a case study of assessing student's coding behavior and skills in a realistic development setting. Students had to solve typical programming problems in the context of app development for the Android platform using the Eclipse IDE. Data was analyzed using IDE as well as browser interaction logs. In addition, screen recordings of the students' interaction with the IDE provide further insight. In this paper we present the first results of our ongoing work.
In the context of a "Smart Grid" research project, together with industrial partners, the OTH-Regensburg realized an intelligent medium-voltage grid in the local area. Goal was to improve the current voltage regulation and to counter the problems with inconsistent energy feed-in of decentralized renewable energy producers. In this paper we discuss the possibilities of using 3rd generation (3G) cellular networks (UMTS) as basic technology to communicate the voltage-levels within a medium-voltage grid. We build an experimental
hardware setup to generate data-traffic as specified for the smart
grid. By analyzing the performance of 3G cellular networks in
terms of transmission latency and rate of failure, we tried to
evaluate the usability of this technology for such critical data
exchange. Though mobile communication in its structure is not
specified for the use of transmitting such infrastructure critical
data, the results show a promising high reliability with low
transmission latency. The experiments served just to test a
fragment of the conditions of use in a real scenario. An expanded
test scope is needed to further analyze the performance of mobile
radio for automatic control in smart grids. In the end the results
discussed in this paper led to a successful prototype of an
intelligent medium-voltage grid with mobile radio as communication technology
An adequate network management is an essential part for each network permitting to keep the network performance at a suitable level. In this paper, we present our work focusing on an Ethernet network which is used as background interconnection technology for a smart home system in large buildings like tenements or an office block. In this case the network is larger and especially the applications are quite heterogeneous as compared to a private smart home system. Therefore, it is hard to supply a fair and quality of service aware network meeting all the demands. This is especially challenging in the case of an Ethernet network because this technology was intended to use it as a transparent connection system without the feature to support hard quality of service. We present how this problem could be solved by a middleware which best meets the special requirement of the mentioned use case. Finally, we discuss possible design improvements of this solution and present the recent Ethernet standards that could help solve this problem in an alternative way.
Holding non-co-located conversationswhile driving is dangerous (Horrey and- Wickens, 2006; Strayer et al., 2006), much more so than conversations with physically present, “situated” interlocutors
(Drews et al., 2004). In-car dialogue systems typically resemble non-co-located conversations more, and share their negative impact (Strayer et al., 2013). We implemented and tested a simple strategy
for making in-car dialogue systems aware of the driving situation, by giving them the capability to interrupt themselves when a dangerous situation is detected,and resume when over. We show that this improves both driving performance and recall of system-presented information,
compared to a non-adaptive strategy.
When humans speak, they do not plan their full utterance inall detail before beginning to speak, nor do they speak piece-by-piece and ignoring their full message – instead humans usepartial representations in which they fill in the missing partsas the utterance unfolds. Incremental speech synthesizers, incontrast, have not yet made use of partial representations and theinformation contained there-in.We analyze the quality of prosodic parameter assignments(pitch and duration) generated from partial utterance specifi-cations (substituting defaults for missing features) in order todetermine the requirements that symbolic incremental prosodymodelling should meet. We find that broader, higher-level infor-mation helps to improve prosody even if lower-level informationabout the near future is yet unavailable. Furthermore, we findthat symbolic phrase-level or utterance-level information is mosthelpful towards the end of the phrase or utterance, respectively,that is, when this information is becoming available even in theincremental case. Thus, the negative impact of incremental pro-cessing can be minimized by using partial representations thatare filled in incrementally.
Automatic speech recognition (ASR) technology has been developed to such a level that off-the-shelf distributed speech recognition services are available (free of cost), which allow researchers to integrate speech into their applications with little development effort or expert knowledge leading to better results compared with previously used open-source tools.
Often, however, such services do not accept language models or grammars but process free speech from any domain. While results are very good given the enormous size of the search space, results frequently contain out-of-domain words or constructs that cannot be understood by subsequent domain-dependent natural language understanding (NLU) components. We present a versatile post-processing technique based on phonetic distance that integrates domain knowledge with open-domain ASR results, leading to improved ASR performance. Notably, our technique is able to make use of domain restrictions using various degrees of domain knowledge, ranging from pure vocabulary restrictions via grammars or N-Grams to restrictions of the acceptable utterances. We present results for a variety of corpora (mainly from human-robot interaction) where our combined approach significantly outperforms Google ASR as well as a plain open-source ASR solution.
Human speakers plan and deliver their utterances incrementally, piece-by-piece, and it is obvious that their choice regarding phonetic details (and the details' peculiarities) is rarely determined by globally optimal solutions. In contrast, parametric speech synthesizers use a full-utterance context when optimizing vocoding parameters and when determing HMM states. Apart from being cognitively implausible, this impedes incremental use-cases, where the future context is often at least partially unavailable. This paper investigates the `locality' of features in parametric speech synthesis voices and takes some missing steps towards better HMM state selection and prosody modelling for incremental speech synthesis.
It is established that driver distraction is the result of sharing cognitive resources between the primary task (driving) and any other secondary task. In the case of holding conversations, a human passenger who is aware of the driving conditions can choose to interrupt his speech in situations potentially requiring more attention from the driver, but in-car information systems typically do not exhibit such sensitivity. We have designed and tested such a system in a driving simulation environment. Unlike other systems, our system delivers information via speech (calendar entries with scheduled meetings) but is able to react to signals from the environment to interrupt when the driver needs to be fully attentive to the driving task and subsequently resume its delivery. Distraction is measured by a secondary short-term memory task. In both tasks, drivers perform significantly worse when the system does not adapt its speech, while they perform equally well to control conditions (no concurrent task) when the system intelligently interrupts and resumes.
When a passenger speaks to a driver, he or she is co-located with the driver, is generally aware of the situation, and can stop speaking to allow the driver to focus on the driving task. In-car dialogue systems ignore these important aspects, making them more distracting than even cell-phone conversations. We developed and tested a "situationally-aware" dialogue system that can interrupt its speech when a situation which requires more attention from the driver is detected, and can resume when driving conditions return to normal. Furthermore, our system allows driver-controlled resumption of interrupted speech via verbal or visual cues (head nods). Over two experiments, we found that the situationally-aware spoken dialogue system improves driving performance and attention to the speech content, while driver-controlled speech resumption does not hinder performance in either of these two tasks
A recently proposed concept for training reverberation-robust acoustic models for automatic speech recognition using pairs of clean and reverberant data is extended from word models to tied-state triphone models in this paper. The key idea of the concept, termed ICEWIND, is to use the clean data for the temporal alignment and the reverberant data for the estimation of the emission densities. Experiments with the 5000-word Wall Street Journal corpus confirm the benefits of ICEWIND with tied-state triphones: While the training time is reduced by more than 90%, the word accuracy is improved at the same time, both for room-specific and multi-style hidden Markov models. Since the acoustic models trained with ICEWIND need less Gaussian components for the emission densities to achieve comparable recognition rates as Baum-Welch acoustic models, ICEWIND also allows for a reduced decoding complexity.
Many MapReduce jobs for analyzing Big Data require many hours and have to be repeated again and again because the base data changes continuously. In this paper we propose Marimba, a framework for making MapReduce jobs incremental. Thus, a recomputation of a job only needs to process the changes since the last computation. This accelerates the execution and enables more frequent recomputations, which leads to results which are more up-to-date. Our approach is based on concepts that are popular in the area of materialized views in relational database systems where a view can be updated only by aggregating changes in base data upon the previous result.
This paper presents ongoing work in incremental speech synthesis that enables a system to adapt speech delivery to unforeseen changes in the timing of motor events (e. g. a robot actuator working faster or slower than anticipated) in order to improve the coordination of speech and gestures for deictic expressions.
In simultaneous interpreting, human experts incrementally construct and extend partial hypotheses about the source speaker’s message, and start to verbalize a corresponding message in the target language, based on a partial translation – which may have to be corrected occasionally. They commence the target utterance in the hope that they will be able to finish understanding the source speaker’s message and determine its translation in time for the unfolding delivery. Of course, both incremental understanding and translation by humans can be garden-pathed, although experts are able to optimize their delivery so as to balance the goals of minimal latency, translation quality and high speech fluency with few corrections. We investigate the temporal properties of both translation input and output to evaluate the tradeoff between low latency and translation quality. In addition, we estimate the improvements that can be gained with a tempo-elastic
speech synthesizer.
Professional software development is a complex task with many inputs and a complex output. In order to handle complex topics as software or complex engineering projects, structured processes as the V-model or iterative development processes exist. Similarly, the development of a software engineering lecture is a task with many inputs, and a complex output. A structured and methodological approach to the development of a lecture is presented, which applies the same principles as used in the development of software.
Learning centered teaching becomes an important factor in a global perspective of learning software engineering. The Just-in-Time Teaching approach is used in a Chinese-German empirical case study. In a one year terminated project we will analyze the performance of our students in an active learning scenario with Just-in-Time Teaching and Peer Instruction. We will contribute an inter-cultural comparison of achieved competencies by student’s self-assessment and teacher’s observation.
Datenbanken ohne Schema?
(2014)
In der Entwicklung von interaktiven Web-Anwendungen sind NoSQL-Datenbanksysteme zunehmend beliebt, nicht zuletzt, weil sie flexible Datenmodelle erlauben. Das erleichtert insbesondere ein agiles Projektmanagement, das sich durch häufige Releases und entsprechend häufige Änderungen am Datenmodell auszeichnet. In diesem Artikel geben wir einen Überblick über die besonderen Herausforderungen der agilen Anwendungsentwicklung gegen schemalose NoSQL-Datenbanksysteme. Wir stellen Strategien für die Schema-Evolution aus der Praxis vor, und postulieren unsere Vision einer eigenen Schema-Management-Komponente für NoSQL-Datenbanksysteme, die für eine kontinuierliche und systematische Schema-Evolution ausgelegt ist.
Ein eigenes Themenheft zum Datenmanagement in der Cloud dient uns als Anlass, die Präsenz von Cloud-Themen in der akademischen Datenbanklehre zu erfassen. In diesem Artikel geben wir die Ergebnisse einer Umfrage innerhalb der Fachgruppe Datenbanksysteme durch den Arbeitskreis Datenmanagement in der Cloud wieder. Dozentinnen und Dozenten von über zwanzig Hochschulen nahmen an der Umfrage teil. Es zeigt sich deutlich, dass sich das Thema „Cloud“ in der Hochschullehre zunehmend etabliert, jedoch überwiegend als ergänzendes Angebot, und seltener in der grundständigen Lehre verankert. Wir fassen die Ergebnisse unserer Umfrage zusammen und wagen Deutungsversuche.