<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>4514</id>
    <completedYear/>
    <publishedYear>2015</publishedYear>
    <thesisYearAccepted/>
    <language>dan</language>
    <pageFirst>11</pageFirst>
    <pageLast>13</pageLast>
    <pageNumber/>
    <edition/>
    <issue>1</issue>
    <volume>2</volume>
    <type>article</type>
    <publisherName>TechMedia</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="dan">Trinvise og delte strategier for kontrol af velfærdsrobotter</title>
    <parentTitle language="dan">Medicoteknik</parentTitle>
    <identifier type="url">http://ipaper.ipapercms.dk/TechMedia/Medicoteknik/2015/1/?Page=11</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Kerstin Fischer</author>
    <author>Leon Bodenhagen</author>
    <author>Norbert Krüger</author>
    <author>Morten Østergaard Andersen</author>
    <author>Timo Baumann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
  </doc>
  <doc>
    <id>4492</id>
    <completedYear/>
    <publishedYear>2014</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>68</pageFirst>
    <pageLast>72</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Association for Computational Linguistics</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Situationally Aware In-Car Information Presentation Using Incremental Speech Generation: Safer, and More Effective</title>
    <abstract language="eng">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&#13;
(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&#13;
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,&#13;
compared to a non-adaptive strategy.</abstract>
    <parentTitle language="eng">Proceedings of the EACL 2014 Workshop on Dialogue in Motion, Gothenburg, Sweden</parentTitle>
    <identifier type="doi">10.3115/v1/W14-0212</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Spyros Kousidis</author>
    <author>Casey Kennington</author>
    <author>Timo Baumann</author>
    <author>Hendrik Buschmeier</author>
    <author>Stefan Kopp</author>
    <author>David Schlangen</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>in-car information presentation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>incremental speech generation</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>situation awareness</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4441</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>329</pageFirst>
    <pageLast>333</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Automatic Detection of Enjambment in German Readout Poetry</title>
    <abstract language="eng">One of the most important patterns in ancient as well as modern poetry is the enjambment, the continuation of a sentence beyond the end of a line, couplet, or stanza. The paper reports first activities towards the development of a digital tool to analyze the accentuation of poetic enjambments in readout poetry. The aim in this contribution is to recognize two forms of enjambment (emphasized and unemphasized) in poems using audio and text data. We use data from lyrikline which is a major online portal for spoken poetry whereas poems are read aloud by the original authors. We identified by hermeneutical means based on literary analysis a total of 69 poems being characteristic for the use of enjambments in modern and postmodern German poetry and train classifiers to differentiate the emphasized/unemphasized ategorization. A remarkable result of our automated analyses (and to our knowledge the first data-driven analysis of this kind) is the identification of a cultural difference in the accentuation of enjambments: statistically speaking, poets from the former GDR tend to emphasize the enjambment, whereas poets from the FRG do not. We use features derived from speech-to-text alignment and statistical parsing information such as pause lengths, number of lines with verbs, and number of lines with punctuation. The best classification results, calculated by the F-measure, for the both types of enjambment (emphasized/unemphasized) is 0.69.</abstract>
    <parentTitle language="eng">Proceedings of Speech Prosody, 2018, Poznán</parentTitle>
    <identifier type="doi">10.21437/SpeechProsody.2018-67</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Hussein Hussein</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <author>Timo Baumann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>modern and postmodern poetry</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>free verse prosody</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>emphasized and unemphasized enjambment</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4438</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2162</pageFirst>
    <pageLast>2166</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Analysing the Focus of a Hierarchical Attention Network: the Importance of Enjambments When Classifying Post-modern Poetry</title>
    <abstract language="eng">After overcoming the traditional metrics, modern and postmodern poetry developed a large variety of ‘free verse prosodies’ that falls along a spectrum from a more fluent to a more disfluent and choppy style. We present a method, grounded in philological analysis and theories on cognitive (dis)fluency, to analyze this ‘free verse spectrum’ into six classes of poetic styles as well as to differentiate three types of poems with enjambments. We use a model for automatic prosodic analysis of spoken free verse poetry which uses deep hierarchical attention networks to integrate the source text and audio and predict the assigned class. We then analyze and fine-tune the model with a particular focus on enjambments and in two ways: we drill down on classification performance by analyzing whether the model focuses on similar traits of poems as humans would, specifically, whether it internally builds a notion of enjambment. We find that our model is similarly good as humans in finding enjambments; however, when we employ the model for classifying enjambment-dominated poem types, it does not pay particular attention to those lines. Adding enjambment labels to the training only marginally improves performance, indicating that all other lines are similarly informative for the model.</abstract>
    <parentTitle language="eng">Proceedings of Interspeech, 2018, Hyderabad</parentTitle>
    <identifier type="doi">10.21437/Interspeech.2018-2533</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <author>Hussein Hussein</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>digital humanities</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>free verse poetry</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>prosodic analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>enjambment detection</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>hierarchical attention network</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4439</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Gesellschaft für Informatik e.V</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Analysis and Classification of Prosodic Styles in Post-modern Spoken Poetry</title>
    <abstract language="eng">We present our research on computer-supported analysis of prosodic styles in post-modern poetry. Our project is unique in making use of both the written as well as the spoken form of the poem as read by the original author. In particular, we use speech and natural language processing technology to align speech and text and to perform textual analyses. We then explore, based on literary theory, the quantitative value of various types of features in differentiating various prosodic classes of post-modern poetry using machine-learning techniques. We contrast this feature-driven approach with a theoretically less informed neural networks-based approach and explore the relative strengths of both models, as well as how to integrate higher-level knowledge into the NN. In this paper, we give an overview of our project, our approach, and particularly focus on the challenges encountered and lessons learned in our interdisciplinary endeavour. The classification results of the rhythmical patterns (six classes) using NN-based approaches are better than by feature-based approaches.</abstract>
    <parentTitle language="eng">INF-DH 2018 Workshopband</parentTitle>
    <identifier type="doi">10.18420/infdh2018-09</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Burkhard Meyer-Sickendiek</author>
    <author>Hussein Hussein</author>
    <author>Timo Baumann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>modern and postmodern poetry</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>free verse prosody</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>rhythmical patters</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4440</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>44</pageFirst>
    <pageLast>49</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Association for Computational Linguistics</publisherName>
    <publisherPlace>Santa Fe, New Mexico</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Analysis of Rhythmic Phrasing: Feature Engineering vs. Representation Learning for Classifying Readout Poetry</title>
    <abstract language="eng">We show how to classify the phrasing of readout poems with the help of machine learning algorithms that use manually engineered features or automatically learn representations. We investigate modern and postmodern poems from the webpage lyrikline, and focus on two exemplary rhythmical patterns in order to detect the rhythmic phrasing: The Parlando and the Variable Foot. These rhythmical patterns have been compared by using two important theoretical works: The Generative Theory of Tonal Music and the Rhythmic Phrasing in English Verse. Using both, we focus on a combination of four different features: The grouping structure, the metrical structure, the time-span-variation, and the prolongation in order to detect the rhythmic phrasing in the two rhythmical types. We use manually engineered features based on text-speech alignment and parsing for classification. We also train a neural network to learn its own representation based on text, speech and audio during pauses. The neural network outperforms manual feature engineering, reaching an f-measure of 0.85.</abstract>
    <parentTitle language="eng">Proceedings of the Second Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL-2018), August 25, 2018, Santa Fe, New Mexico, USA</parentTitle>
    <identifier type="url">https://aclanthology.org/W18-4505</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <author>Hussein Hussein</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4465</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1929</pageFirst>
    <pageLast>1940</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Style Detection for Free Verse Poetry from Text and Speech</title>
    <abstract language="deu">Modern and post-modern free verse poems feature a large and complex variety in their poetic prosodies that falls along a continuum from a more fluent to a more disfluent and choppy style. As the poets of modernism overcame rhyme and meter, they oriented themselves in these two opposing directions, creating a free verse spectrum that calls for new analyses of prosodic forms. We present a method, grounded in philological analysis and current research on cognitive (dis)fluency, for automatically analyzing this spectrum. We define and relate six classes of poetic styles (ranging from parlando to lettristic decomposition) by their gradual differentiation. Based on this discussion, we present a model for automatic prosodic classification of spoken free verse poetry that uses deep hierarchical attention networks to integrate the source text and audio and predict the assigned class. We evaluate our model on a large corpus of German author-read post-modern poetry and find that classes can reliably be differentiated, reaching a weighted f-measure of 0.73, when combining textual and phonetic evidence. In our further analyses, we validate the model’s decision-making process, the philologically hypothesized continuum of fluency and investigate the relative importance of various features.</abstract>
    <parentTitle language="eng">Proceedings of the 27th International Conference on Computational Linguistics (COLING), 20-26.08.2018, Santa Fe, New Mexico, USA</parentTitle>
    <identifier type="url">https://aclanthology.org/C18-1164.pdf</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Timo Baumann</author>
    <author>Hussein Hussein</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <collection role="ddc" number="006">Spezielle Computerverfahren</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4437</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2157</pageFirst>
    <pageLast>2161</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">An Empirical Analysis of the Correlation of Syntax and Prosody</title>
    <abstract language="eng">The relation of syntax and prosody (the syntax-prosody interface) has been an active area of research, mostly in linguistics and typically studied under controlled conditions. More recently, prosody has also been successfully used in the data-based training of syntax parsers. However, there is a gap between the controlled and detailed study of the individual effects between syntax and prosody and the large-scale application of prosody in syntactic parsing with only a shallow analysis of the respective influences. In this paper, we close the gap by investigating the significance of correlations of prosodic realization with specific syntactic functions using linear mixed effects models in a very large corpus of read-out German encyclopedic texts. Using this corpus, we are able to analyze prosodic structuring performed by a diverse set of speakers while they try to optimize factual content delivery. After normalization by speaker, we obtain significant effects, e.g. confirming that the subject function, as compared to the object function, has a positive effect on pitch and duration of a word, but a negative effect on loudness.</abstract>
    <parentTitle language="eng">Proceedings of Interspeech 2018, 02.-06.09.2018, Hyderabad</parentTitle>
    <identifier type="doi">10.21437/Interspeech.2018-2530</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Arne Köhn</author>
    <author>Timo Baumann</author>
    <author>Oskar Dörfler</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>syntax</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>prosody</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>corpus-based analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>linear mixed effects models</value>
    </subject>
    <collection role="ddc" number="418">Standardsprache; Angewandte Linguistik</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4442</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace>Hyderabad, India</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">DialogOS: Simple and extensible dialog modeling</title>
    <abstract language="eng">We present the open-source extensible dialog manager DialogOS.&#13;
DialogOS features simple finite-state based dialog management&#13;
(which can be expanded to more complex DM strategies via a full-fledged scripting language) in combination with integrated speech recognition and synthesis in multiple languages.&#13;
DialogOS runs on all major platforms, provides a simple-to-use&#13;
graphical interface and can easily be extended via well-defined&#13;
plugin and client interfaces, or can be integrated server-side into&#13;
larger existing software infrastructures. We hope that DialogOS&#13;
will help foster research and teaching given that it lowers the bar&#13;
of entry into building and testing spoken dialog systems and provides paths to extend one’s system as development progresses.</abstract>
    <parentTitle language="eng">Proceedings of Interspeech: Hyderabad, India 2-6 September 2018</parentTitle>
    <identifier type="url">https://edoc.sub.uni-hamburg.de/informatik/volltexte/2018/246/pdf/koller_dialogOS.pdf</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Alexander Koller</author>
    <author>Timo Baumann</author>
    <author>Arne Köhn</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4445</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>819</pageFirst>
    <pageLast>822</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Learning to Determine Who is the Better Speaker</title>
    <abstract language="eng">Speech can be more or less likable in various ways and comparing speakers by likability has important applications such as speaker selection or matching. Determining the likability of a speaker is a difficult task which can be simplified by breaking it down into pairwise preference decisions. Using a corpus of 5440 pairwise preference ratings collected previously through crowd-sourcing, we train classifiers to determine which of two speakers is “better”. We find that modeling the speech feature sequences using LSTMs outperforms conventional methods that pre-aggregate feature averages by a large margin, indicating that the prosodic structure should be taken into account when determining speech quality. Our classifier reaches an accuracy of 97 % for coarse-grained decisions, where differences between speech quality in both stimuli is relatively large.</abstract>
    <parentTitle language="eng">Proceedings of the 9th International Conference on Speech Prosody,  13-16 June 2018, Poznań, Poland</parentTitle>
    <identifier type="doi">10.21437/SpeechProsody.2018-165</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:06:06+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <collection role="ddc" number="006">Spezielle Computerverfahren</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4466</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>154</pageFirst>
    <pageLast>194</pageLast>
    <pageNumber/>
    <edition/>
    <issue>10</issue>
    <volume>6</volume>
    <type>conferenceobject</type>
    <publisherName>Schloss Dagstuhl ‐ Leibniz-Zentrum für Informatik</publisherName>
    <publisherPlace>Dagstuhl, Germany</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Highly Responsive Vocal Interaction through Incremental Processing</title>
    <abstract language="eng">This seminar was held in late 2016 and brought together, for the first time, researchers studying vocal interaction in a variety of different domains covering communications between all possible combinations of humans, animals, and robots. While each of these sub-domains has extensive histories of research progress, there is much potential for cross-fertilisation that currently remains underexplored. This seminar aimed at bridging this gap. In this report, we present the nascent research field of VIHAR and the major outputs from our seminar in the form of prioritised open research questions, abstracts from stimulus talks given by prominent researchers in their respective fields, and open problem statements by all participants.</abstract>
    <parentTitle language="eng">Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR), October 30-4, 2016</parentTitle>
    <identifier type="doi">10.4230/DagRep.6.10.154</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <author>Timo Baumann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4468</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2189</pageFirst>
    <pageLast>2200</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Gesellschaft für Informatik</publisherName>
    <publisherPlace>Bonn</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Rhythmicalizer: Data Analysis for the Identification of Rhythmic Patterns in Readout Poetry</title>
    <abstract language="eng">The most important development in modern and postmodern poetry is the replacement of traditional meter by new rhythmical patterns. Ever since Walt Whitman's Leaves of Grass (1855), modern (nineteenth-to twenty-first-century) poets have been searching for novel forms of prosody, accent, rhythm, and intonation. Along with the rejection of older metrical units such as the iamb or trochee, a structure of lyrical language was developed that renounced traditional forms like rhyme and meter. This development is subsumed under the term free verse prosody. Our project will test this theory by applying machine learning or deep learning techniques to a corpus of modern and postmodern poems as read aloud by the original authors. To this end, we examine “lyrikline”, the most famous online portal for spoken poetry. First, about 17 different patterns being characteristic for the lyrikline-poems have been identified by the philological scholar of this project. This identification was based on a certain philological method including three different steps: a) grammetrical ranking; b) rhythmic phrasing; and c) mapping rubato and prosodic phrasing. In this paper we will show how to combine this philological and a digital analysis by using the prosody detection available in speech processing technology. In order to analyse the data, we want to use different tools for the following tasks: PoS-tagging, alignment, intonation, phrases and pauses, and tempo. We also analyzed the lyrikline-data by identifying the occurrence of the mentioned patterns. This analysis is a first step towards an automatic classification based on machine learning or deep learning techniques.</abstract>
    <parentTitle language="eng">INFORMATIK 2017, Tagung vom 25.- 29. September 2017 in Chemnitz</parentTitle>
    <parentTitle language="mul">GI-Edition Lecture notes in informatics. Proceedings ; volume P-275</parentTitle>
    <identifier type="doi">10.18420/in2017_218</identifier>
    <identifier type="isbn">978-3-88579-669-5</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Creative Commons - CC-BY-NC - Namensnennung - Nicht kommerziell 3.0 International</licence>
    <author>Burkhard Meyer-Sickendiek</author>
    <author>Hussein Hussein</author>
    <author>Timo Baumann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4470</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>125</pageFirst>
    <pageLast>130</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>The COLING 2016 Organizing Committee</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Large-scale Analysis of Spoken Free-verse Poetry</title>
    <abstract language="eng">Most modern and post-modern poems have developed a post-metrical idea of lyrical prosody that employs rhythmical features of everyday language and prose instead of a strict adherence to rhyme and metrical schemes. This development is subsumed under the term free verse prosody. We present our methodology for the large-scale analysis of modern and post-modern poetry in both their written form and as spoken aloud by the author. We employ language processing tools to align text and speech, to generate a null-model of how the poem would be spoken by a naïve reader, and to extract contrastive prosodic features used by the poet. On these, we intend to build our model of free verse prosody, which will help to understand, differentiate and relate the different styles of free verse poetry. We plan to use our processing scheme on large amounts of data to iteratively build models of styles, to validate and guide manual style annotation, to identify further rhythmical categories, and ultimately to broaden our understanding of free verse poetry. In this paper, we report on a proof-of-concept of our methodology using smaller amounts of poems and a limited set of features. We find that our methodology helps to extract differentiating features in the authors’ speech that can be explained by philological insight. Thus, our automatic method helps to guide the literary analysis and this in turn helps to improve our computational models.</abstract>
    <parentTitle language="eng">Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities, Osaka, Japan, December 11-17 2016</parentTitle>
    <identifier type="url">https://aclanthology.org/W16-4017</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4477</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>178</pageFirst>
    <pageLast>182</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Tonality in Language: The Generative Theory of Tonal Music as a Framework for Prosodic Analysis of Poetry</title>
    <abstract language="eng">This contribution focuses on structural similarities between tonality and cadences in music on the one hand, and rhythmical patterns in poetic languages respectively poetry on the other hand.&#13;
We investigate two exemplary rhythmical patterns in modern and postmodern poetry to detect these tonality-like features in poetic language: The Parlando and the Variable Foot. German poems&#13;
readout from the original poets are collected from the webpage of our partner lyrikline. We compared these rhythmical features with tonality rules, explained in two important theoretical volumes: The Generative Theory of Tonal Music and the Rhythmic Phrasing in English Verse. Using both volumes, we focused on a certain combination of four different features: The grouping&#13;
structure, the metrical structure, the time-span-variation and the prolongation, in order to detect the two important rhythmical patterns which use tonality-like features in poetic language (Parlando and Variable Foot). Different features including pause and parser information are used in this classification process. The best classification result, calculated by the f-measure, for&#13;
Parlando and Variable Foot is 0.69.</abstract>
    <parentTitle language="eng">6th International Symposium on Tonal Aspects of Languages (TAL 2018), 18-20 June 2018, Berlin, Germany</parentTitle>
    <identifier type="doi">10.21437/TAL.2018-36</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="ConferenceStatement">International Symposium on Tonal Aspects of Languages, 6, 2018, Berlin</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Hussein Hussein</author>
    <author>Burkhard Meyer-Sickendiek</author>
    <author>Timo Baumann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>tonality in poetic language</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>prosodic patterns in postwar poems</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>automatic detection of prosodic features</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4467</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>421</pageFirst>
    <pageLast>432</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>bookpart</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Singapore</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Recognising Conversational Speech: What an Incremental ASR Should Do for a Dialogue System and How to Get There</title>
    <abstract language="eng">Automatic speech recognition (ASR) is not only becoming increasingly accurate, but also increasingly adapted for producing timely, incremental output. However, overall accuracy and timeliness alone are insufficient when it comes to interactive dialogue systems which require stability in the output and responsivity to the utterance as it is unfolding. Furthermore, for a dialogue system to deal with phenomena such as disfluencies, to achieve deep understanding of user utterances these should be preserved or marked up for use by downstream components, such as language understanding, rather than be filtered out. Similarly, word timing can be informative for analyzing deictic expressions in a situated environment and should be available for analysis. Here we investigate the overall accuracy and incremental performance of three widely used systems and discuss their suitability for the aforementioned perspectives. From the differing performance along these measures we provide a picture of the requirements for incremental ASR in dialogue systems and describe freely available tools for using and evaluating incremental ASR.</abstract>
    <parentTitle language="eng">Dialogues with social robots: Enablements analyses and evaluation</parentTitle>
    <parentTitle language="mul">Lecture Notes in Electrical Engineering: Bd. 427</parentTitle>
    <identifier type="isbn">978-981-10-2584-6</identifier>
    <identifier type="doi">10.1007/978-981-10-2585-3_35</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <author>Casey Kennington</author>
    <author>Julian Hough</author>
    <author>David Schlangen</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Incremental ASR</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Conversational speech</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>System requirements</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Evaluation</value>
    </subject>
    <collection role="ddc" number="006">Spezielle Computerverfahren</collection>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4481</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>268</pageFirst>
    <pageLast>277</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>The COLING 2016 Organizing Committee</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Predictive Incremental Parsing Helps Language Modeling</title>
    <abstract language="eng">Predictive incremental parsing produces syntactic representations of sentences as they are produced, e.g. by typing or speaking. In order to generate connected parses for such unfinished sentences, upcoming word types can be hypothesized and structurally integrated with already realized words. For example, the presence of a determiner as the last word of a sentence prefix may indicate that a noun will appear somewhere in the completion of that sentence, and the determiner can be attached to the predicted noun. We combine the forward-looking parser predictions with backward-looking N-gram histories and analyze in a set of experiments the impact on language models, i.e. stronger discriminative power but also higher data sparsity. Conditioning N-gram models, MaxEnt models or RNN-LMs on parser predictions yields perplexity reductions of about 6%. Our method (a) retains online decoding capabilities and (b) incurs relatively little computational overhead which sets it apart from previous approaches that use syntax for language modeling. Our method is particularly attractive for modular systems that make use of a syntax parser anyway, e.g. as part of an understanding pipeline where predictive parsing improves language modeling at no additional cost.</abstract>
    <parentTitle language="eng">Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, Japan</parentTitle>
    <identifier type="url">https://aclanthology.org/C16-1026</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Arne Köhn</author>
    <author>Timo Baumann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4478</id>
    <completedYear/>
    <publishedYear>2017</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2262</pageFirst>
    <pageLast>2266</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ISCA</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Large-Scale Speaker Ranking from Crowdsourced Pairwise Listener Ratings</title>
    <abstract language="eng">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 frequently, generalizations are useful and there is often a broad intersubjective consensus about whether one speaker is more likable than another. However, breaking down likability rankings into pairwise comparisons leads to a quadratic explosion of rating pairs. We present a methodology and software to efficiently create a likability ranking for many speakers from crowdsourced pairwise likability ratings. We collected pairwise likability ratings for many (&gt;220) speakers from many raters (&gt;160) and turn these ratings into one likability ranking. We investigate the resulting speaker ranking stability under different conditions: limiting the number of ratings and the dependence on rater and speaker characteristics. We also analyze the ranking wrt. acoustic correlates to find out what factors influence likability. We publish our ranking and the underlying ratings in order to facilitate further research.</abstract>
    <parentTitle language="eng">Interspeech 2017 : 20-24 August 2017</parentTitle>
    <identifier type="doi">10.21437/Interspeech.2017-1697</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Timo Baumann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>ranking</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>speech quality</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>likability</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>found data</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>ratings</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>crowd-sourcing</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4480</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>9</pageFirst>
    <pageLast>13</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Navigating the Spoken Wikipedia</title>
    <abstract language="eng">The Spoken Wikipedia project unites volunteer readers of encyclopedic entries. Their recordings make encyclopedic knowledge accessible to persons who are unable to read (out of alexia, visual impairment, or because their sight is currently occupied, e. g. while driving). However, on Wikipedia, recordings are available as raw audio files that can only be consumed linearly, without the possibility for targeted navigation or search. We present a reading application which uses an alignment between the recording, text and article structure and which allows to navigate spoken articles, through a graphical or voice-based user interface (or a combination thereof). We present the results of a usability study in which we compare the two interaction modalities. We find that both types of interaction enable users to navigate articles and to find specific information much more quickly compared to a sequential presentation of the full article. In particular when the VUI is not restricted by speech recognition and understanding issues, this interface is on par with the graphical interface and thus a real option for browsing the Wikipedia without the need for vision or reading.</abstract>
    <parentTitle language="eng">Proceedings of the 7th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT 2016)</parentTitle>
    <identifier type="doi">10.21437/SLPAT.2016-2</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Marcel Rohde</author>
    <author>Timo Baumann</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Mensch-Maschine-Interaktion</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Sprechschnittstelle</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Sprachdialogverarbeitung</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4479</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4644</pageFirst>
    <pageLast>4647</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>European Language Resources Association (ELRA)</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Mining the Spoken Wikipedia for Speech Data and Beyond</title>
    <abstract language="eng">We present a corpus of time-aligned spoken data of Wikipedia articles as well as the pipeline that allows to generate such corpora for many&#13;
languages. There are initiatives to create and sustain spoken Wikipedia versions in many languages and hence the data is freely available,&#13;
grows over time, and can be used for automatic corpus creation. Our pipeline automatically downloads and aligns this data. The resulting&#13;
German corpus currently totals 293h of audio, of which we align 71h in full sentences and another 86h of sentences with some missing&#13;
words. The English corpus consists of 287h, for which we align 27h in full sentence and 157h with some missing words. Results are publically available.</abstract>
    <parentTitle language="eng">Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)</parentTitle>
    <identifier type="url">https://aclanthology.org/L16-1735</identifier>
    <enrichment key="opus.import.date">2022-06-20T18:36:30+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Arne Köhn</author>
    <author>Florian Stegen</author>
    <author>Timo Baumann</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Spoken Wikipedia</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Long Audio Alignment</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Speech Resource</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>4469</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Gesellschaft für Informatik e.V.</publisherName>
    <publisherPlace>Aachen</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Entwicklung und Evaluierung einer Notenwender-App für Klaviernoten</title>
    <abstract language="deu">Das ständige Umblättern von Noten ist für Musiker ein wiederkehrendes Problem. Dieses wird häufig durch einen Assistenten des Musikers, dem sogenannten Notenwender, gelöst. Diese Unterstützung haben allerdings viele Musiker nur selten während des Übens. In diesem Artikel stellen wir eine Anwendung für mobile Geräte vor, die auf verschiedene Arten das Umblättern von Klavierpartituren unterstützt. In einer Studie mit professionellen Musikern und Klavierschülern wurden diese Arten gegeneinander abgewogen. Die Ergebnisse zeigen auf, dass computer-unterstütztes Blättern Vorteile gegenüber herkömmlichem Blättern hat.</abstract>
    <parentTitle language="deu">Mensch und Computer 2016 - Tagungsband, 4. - 7. September 2016, Aachen</parentTitle>
    <identifier type="doi">10.18420/muc2016-mci-0159</identifier>
    <enrichment key="opus.import.date">2022-06-20T17:22:32+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Kolja Kirsch</author>
    <author>Frank Steinicke</author>
    <author>Timo Baumann</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othpublikationsherkunft" number="">Externe Publikationen</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
</export-example>
