@inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {How to identify elliptical poems within a digital corpus of auditory poetry}, series = {Elektronische Sprachsignalverarbeitung 2019 (ESSV), Tagungsband der 30. Konferenz, Dresden, 3.-8. M{\"a}rz 2019}, booktitle = {Elektronische Sprachsignalverarbeitung 2019 (ESSV), Tagungsband der 30. Konferenz, Dresden, 3.-8. M{\"a}rz 2019}, editor = {Birkholz, Peter and Stone, Simon}, publisher = {TUDpress}, address = {Dresden, Germany}, isbn = {978-3-959081-57-3}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:18-228-7-2579}, pages = {247 -- 254}, abstract = {Ellipses denote the omission of one or more grammatically necessary phrases. In this paper, we will demonstrate how to identify such ellipses as a rhythmical pattern in modern and postmodern free verse poetry by using data from lyrikline which contain the corresponding audio recording of each poem as spoken by the original author. We present a feature engineering approach based on literary analysis as well as a neural networks based approach for the identification of ellipses within the lines of a poem. A contrast class to the ellipsis is defined from poems consisting of complete and correct sentences. The feature-based approach used features derived from a parser such as verb, comma, and sentence ending punctuation. The classifier of neural networks is trained on the line level to integrate the textual information, the spoken recitation, and the pause information between lines, and to integrate information across the lines within the poem. A statistic analysis of poet's gender showed that 65\% of all elliptical poems were written by female poets. The best results, calculated by the weighted F-measure, for the classification of ellipsis with the contrast class is 0.94 with the neural networks based approach. The best results for classification of elliptical lines is 0.62 with the feature-based approach.}, language = {en} } @misc{MeyerSickendiekHusseinBaumann, author = {Meyer-Sickendiek, Burkhard and Hussein, Hussein and Baumann, Timo}, title = {From Fluency To Disfluency: Ranking Prosodic Features Of Poetry By Using Neural Networks}, series = {Proceedings of the International Conference on Digital Humanities (DH 2019), Utrecht, the Netherlands 9-12 July, 2019}, journal = {Proceedings of the International Conference on Digital Humanities (DH 2019), Utrecht, the Netherlands 9-12 July, 2019}, doi = {10.34894/EGZNMI}, language = {en} } @article{BaumannKoehnHennig, author = {Baumann, Timo and K{\"o}hn, Arne and Hennig, Felix}, title = {The Spoken Wikipedia Corpus collection: Harvesting, alignment and an application to hyperlistening}, series = {Language Resources and Evaluation}, volume = {53}, journal = {Language Resources and Evaluation}, number = {2}, publisher = {Springer Nature}, doi = {10.1007/s10579-017-9410-y}, pages = {303 -- 329}, abstract = {Spoken corpora are important for speech research, but are expensive to create and do not necessarily reflect (read or spontaneous) speech 'in the wild'. We report on our conversion of the preexisting and freely available Spoken Wikipedia into a speech resource. The Spoken Wikipedia project unites volunteer readers of Wikipedia articles. There are initiatives to create and sustain Spoken Wikipedia versions in many languages and hence the available data grows over time. Thousands of spoken articles are available to users who prefer a spoken over the written version. We turn these semi-structured collections into structured and time-aligned corpora, keeping the exact correspondence with the original hypertext as well as all available metadata. Thus, we make the Spoken Wikipedia accessible for sustainable research. We present our open-source software pipeline that downloads, extracts, normalizes and text-speech aligns the Spoken Wikipedia. Additional language versions can be exploited by adapting configuration files or extending the software if necessary for language peculiarities. We also present and analyze the resulting corpora for German, English, and Dutch, which presently total 1005 h and grow at an estimated 87 h per year. The corpora, together with our software, are available via http://islrn.org/resources/684-927-624-257-3/. As a prototype usage of the time-aligned corpus, we describe an experiment about the preferred modalities for interacting with information-rich read-out hypertext. We find alignments to help improve user experience and factual information access by enabling targeted interaction.}, language = {en} } @inproceedings{SabooBaumann, author = {Saboo, Ashutosh and Baumann, Timo}, title = {Integration of Dubbing Constraints into Machine Translation}, series = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, booktitle = {Proceedings of the Fourth Conference on Machine Translation, Volume 1: Research Papers}, editor = {Bojar, Ondřej and Chatterjee, Rajen and Federmann, Christian and Fishel, Mark and Graham, Yvette and Haddow, Barry and Huck, Matthias and Yepes, Antonio Jimeno and Koehn, Philipp and Martins, Andr{\´e} and Monz, Christof and Negri, Matteo and N{\´e}v{\´e}ol, Aur{\´e}lie and Neves, Mariana and Post, Matt and Turchi, Marco and Verspoor, Karin}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, doi = {10.18653/v1/W19-5210}, pages = {94 -- 101}, abstract = {Translation systems aim to perform a meaning-preserving conversion of linguistic material (typically text but also speech) from a source to a target language (and, to a lesser degree, the corresponding socio-cultural contexts). Dubbing, i.e., the lip-synchronous translation and revoicing of speech adds to this constraints about the close matching of phonetic and resulting visemic synchrony characteristics of source and target material. There is an inherent conflict between a translation's meaning preservation and 'dubbability' and the resulting trade-off can be controlled by weighing the synchrony constraints. We introduce our work, which to the best of our knowledge is the first of its kind, on integrating synchrony constraints into the machine translation paradigm. We present first results for the integration of synchrony constraints into encoder decoder-based neural machine translation and show that considerably more 'dubbable' translations can be achieved with only a small impact on BLEU score, and dubbability improves more steeply than BLEU degrades.}, language = {en} } @inproceedings{HusseinMeyerSickendiekBaumann, author = {Hussein, Hussein and Meyer-Sickendiek, Burkhard and Baumann, Timo}, title = {Identification of Concrete Poetry within a Modern-Poetry Corpus using Neural Networks}, series = {Proceedings of the Quantitative Approaches to Versification Conference}, booktitle = {Proceedings of the Quantitative Approaches to Versification Conference}, address = {Prague, Czech Republic}, pages = {95 -- 104}, abstract = {This work aims to discern the poetics of concrete poetry by using a corpus-based classification focusing on the two most important techniques used within concrete poetry: semantic decomposition and syntactic permutation. We demonstrate how to identify concrete poetry in modern and postmodern free verse. A class contrasting to concrete poetry is defined on the basis of poems with complete and correct sentences. We used the data from lyrikline, which contain both the written as well as the spoken form of poems as read by the original author. We explored two approaches for the identification of concrete poetry. The first is based on the definition of concrete poetry in literary theory by the extraction of various types of features derived from a parser, such as verb, noun, comma, sentence ending, conjunction, and asemantic material. The second is a neural network-based approach, which is theoretically less informed by human insight, as it does not have access to features established by scholars. This approach used the following inputs: textual information and the spoken recitation of poetic lines as well as information about pauses between lines. The results based on the neural network are more accurate than the feature-based approach. The best results, calculated by the weighted F-measure, for the classification of concrete poetry vis-{\`a}-vis the contrasting class is 0.96}, language = {en} } @inproceedings{TsaiBaumannPecuneetal., author = {Tsai, Vivian and Baumann, Timo and Pecune, Florian and Cassell, Justine}, title = {Faster Responses Are Better Responses: Introducing Incrementality into Sociable Virtual Personal Assistants}, series = {9th International Workshop on Spoken Dialogue System Technology}, volume = {579}, booktitle = {9th International Workshop on Spoken Dialogue System Technology}, editor = {D'Haro, Luis Fernando and Banchs, Rafael E. and Li, Haizhou}, publisher = {Springer Singapore}, address = {Singapore}, isbn = {978-981-13-9442-3}, issn = {1876-1119}, doi = {10.1007/978-981-13-9443-0_10}, pages = {111 -- 118}, abstract = {Speech-based interactive systems, such as virtual personal assistants, inevitably use complex architectures, with a multitude of modules working in series (or less often in parallel) to perform a task (e.g., giving personalized movie recommendations via dialog). Add modules for evoking and sustaining sociability with the user and the accumulation of processing latencies through the modules results in considerable turn-taking delays. We introduce incremental speech processing into the generation pipeline of the system to overcome this challenge with only minimal changes to the system architecture, through partial underspecification that is resolved as necessary. A user study with a sociable movie recommendation agent objectively diminishes turn-taking delays; furthermore, users not only rate the incremental system as more responsive, but also rate its recommendation performance as higher.}, language = {en} } @inproceedings{BaumannHusseinMeyerSickendieketal., author = {Baumann, Timo and Hussein, Hussein and Meyer-Sickendiek, Burkhard and Elbeshausen, Jasper}, title = {A Tool for Human-in-the-Loop Analysis and Exploration of (not only) Prosodic Classifications for Post-modern Poetry}, series = {Informatik 2019 : 50 Jahre Gesellschaft f{\"u}r Informatik Workshop-Beitr{\"a}ge Fachtagung vom 23.-26. September 2019 in Kassel}, booktitle = {Informatik 2019 : 50 Jahre Gesellschaft f{\"u}r Informatik Workshop-Beitr{\"a}ge Fachtagung vom 23.-26. September 2019 in Kassel}, editor = {Draude, Claude and Lange, Martin and Sick, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik}, address = {Bonn}, isbn = {978-3-88579-689-3}, pages = {151 -- 156}, abstract = {Data-based analyses are becoming more and more common in the Digital Humanities and tools are needed that focus human efforts on the most interesting and important aspects of exploration, analysis and annotation by using active machine learning techniques. We present our ongoing work on a tool that supports classification tasks for spoken documents (in our case: read-out post-modern poetry) using a neural networks-based classification backend and a web-based exploration and classification environment.}, language = {en} }