{"title":"Need for automatically generated narration","authors":"David A. Evans, John B. Reichenbach","doi":"10.1145/2390116.2390130","DOIUrl":"https://doi.org/10.1145/2390116.2390130","url":null,"abstract":"This paper argues that the best current text-to-speech (TTS) synthesis systems are approaching the quality necessary to provide effective automated narration of audio books. Currently, nearly all audio books and audio journals are recorded by professional voice actors at great expense with significant lead times. These cost and time constraints mean that fewer than than 2% of the new titles published each year are available in \"Talking Book\" editions, leaving the visually-impaired and print-disabled community of users with few options when seeking material in digital libraries. State-of-the-art TTS systems now can reproduce human voice prosody of sufficient quality to make listening to long narrative reading both pleasant and comprehensible. Such technology is relatively compact and inexpensive; it is time to deploy it widely as an alternative means of accessing digital texts. This would not only directly benefit the reading-disabled community, but also enable \"digital natives\" and other users to listen to texts on platforms on which reading may not be practical.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"62 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120931125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Search and exploration of scanned books","authors":"Marc-Allen Cartright, Jeffrey Dalton, James Allan","doi":"10.1145/2390116.2390122","DOIUrl":"https://doi.org/10.1145/2390116.2390122","url":null,"abstract":"In this demo, we present Proteus, a novel interface for interacting with multiple retrieval types extracted from scanned books provided by the Internet Archive. The primary purpose of Proteus is to provide a rich interactive experience for users to explore collections with automatically extracted and linked entity data. The system supports seamlessly shifting perspectives between books, entities, and topics. Proteus provides a starting point for a variety of exploratory search tasks.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114460880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Roman Rädle, Andreas Weiler, Stephan Huber, Hans-Christian Jetter, Svetlana Mansmann, Harald Reiterer, M. Scholl
{"title":"eBook meets tabletop: using collaborative visualization for search and serendipity in on-line book repositories","authors":"Roman Rädle, Andreas Weiler, Stephan Huber, Hans-Christian Jetter, Svetlana Mansmann, Harald Reiterer, M. Scholl","doi":"10.1145/2390116.2390120","DOIUrl":"https://doi.org/10.1145/2390116.2390120","url":null,"abstract":"The ever-growing amount of digitized books and electronically published documents necessitates proper tools to search and explore such large digital information spaces. This paper presents the design of an interactive prototype for collaborative visual information seeking (VIS) in an on-line book repository. The main objectives of the prototype are a visual metaphor to query an on-line book repository and the facilitation of back-and-forth comparison of search results. Furthermore, an integrated cosine similarity search encourages for serendipitous discoveries while browsing through an information space.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128779235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Personalized recommendations on books for K-12 readers","authors":"M. S. Pera, Yiu-Kai Ng","doi":"10.1145/2390116.2390124","DOIUrl":"https://doi.org/10.1145/2390116.2390124","url":null,"abstract":"Learning to read efficiently and effectively is emphasized at the elementary and high school levels. Finding books that children/youth are interested in reading, however, is a non-trivial task due to the diversity of topics and different readability levels covered in the huge volume of books available these days. Ideally, K-12 students can turn to book recommenders which suggest books that match their interests. However, since the preferences and reading levels of these students vary from one grade to another, books suggested by existing recommenders, which ignore the literacy skills and the personal interests of their users, may be unsuitable for the targeted audience. In this paper, we present additional design issues that should be applied in developing a book recommender based on BReK12, our previously-proposed book recommender for K-12 users, to further enhance the quality of its recommendations. BReK12, which performs content and readability analysis to identify books potentially appealing to its users, is extended to incorporate (i) a multi-criteria analysis that studies its users' complex and diverse interests and (ii) an enhanced readability-detection tool that determines precisely the readability levels of books which match the literary skills of its users.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"27 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120903274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spread co-citation relationship as a measure for document retrieval","authors":"Masaki Eto","doi":"10.1145/2390116.2390121","DOIUrl":"https://doi.org/10.1145/2390116.2390121","url":null,"abstract":"This paper proposes a measure that uses a spread co-citation relationship for document retrieval. To clarify whether this proposed measure has potential for enhancing the search performance of co-citation searching, two retrieval methods are evaluated: one uses the relationship directly; the other incorporates the co-citation context. Experiments with a special test collection comprising about 152,000 documents are conducted. Results indicate that this relationship tends to be able to detect relevant documents which are undetectable using a traditional co-citation relationship, and that using context has a positive effect to reduce the number of noise documents.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132844148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The future of digital","authors":"Natasa Milic-Frayling","doi":"10.1145/2390116.2390127","DOIUrl":"https://doi.org/10.1145/2390116.2390127","url":null,"abstract":"Digital media has transformed the ways in which we process data and information. With the power of modern computing technologies, we can gather, analyze, replicate, and transfer digital content at unprecedented speeds and scale. These advantages stimulate the digitization of physical books, manuscripts, and documents to make them an integral part of the digital repositories. However, transforming physical artifacts into digital formats places them in the same vulnerable position of the born digital content: there is no insurance that the content will be accessible in the future. We reflect on the unique nature of digital media and research needed to devise effective methods and techniques to facilitate long term access to digital content.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131841090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Revisiting the future of reading: the research and design behind XFR","authors":"Maribeth Back","doi":"10.1145/2390116.2390118","DOIUrl":"https://doi.org/10.1145/2390116.2390118","url":null,"abstract":"Reading is part of how we understand the world, how we share knowledge, how we play, and even how we think. Although reading text is the dominant form of reading, most of the text we read letters, numbers, words, and sentences is surrounded by illustrations, photographs, and other kinds of symbols that we include as we read. As dynamic displays migrate into the real world at many scales, whether personal devices, handhelds, or large screens in both interior and exterior spaces, opportunities for reading migrate as well. As has happened continually throughout the history of reading, new technologies, physical forms and social patterns create new genres, which themselves may then combine or collide to morph into something new.\u0000 At PARC, the RED (Research in Experimental Design) group examined emerging technologies for impact on media and the human relationship to information, especially reading. We explored new ways of experiencing text: new genres, new styles of interaction, and unusual media. Among the questions we considered: how might \"the book\" change? How does the experience of reading change with the introduction of new technologies, and how does authoring change?\u0000 In this talk, we'll discuss the ideas behind the design and research process that led to creating eleven different experiences of new forms of reading for a museum exhibit called \"XFR: eXperiments in the Future of Reading\". We'll also consider how our technological context for reading has changed in recent years, and what influence the lessons from XFR may have on our ever-developing online reading experiences.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127832275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Accessible, large-print, listening & talking e-book (ALIT)","authors":"A. Attarwala, R. Baecker, Cosmin Munteanu","doi":"10.1145/2390116.2390129","DOIUrl":"https://doi.org/10.1145/2390116.2390129","url":null,"abstract":"The ALLT e-book is an iPad application that extends the capabilities of standard e-book readers. It provides the capabilities of electronic large-print and talking books. ALLT further adds the ability to synchronize an audio recording of a user reading aloud with the text. Originally conceived to enable visually impaired users to re-experience a reading session with a loved one through replaying a recording of the session, ALLT has been expanded to serve the needs of individuals with a variety of sensory and motor impairments. In this position paper we present the key features of ALLT and expand upon the description presented in our first paper [1].","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121697082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stylometric relevance-feedback towards a hybrid book recommendation algorithm","authors":"P. Vaz, David Martins de Matos, Bruno Martins","doi":"10.1145/2390116.2390125","DOIUrl":"https://doi.org/10.1145/2390116.2390125","url":null,"abstract":"Reading is an important activity for individuals. Content-based recommendation systems are, typically, used to recommend scientific papers or news, where search is driven by topic. Literary reading or reading for leisure differs from scientific reading, because users search books not only for their topic but also by author or writing style. Choosing a new book to read can be tricky and recommendation systems can make it easy by selecting books that the user will like. In this paper we study recommendation through writing style and the influence of negative examples in user preferences. Our experiments were conducted in a hybrid set-up that combines a collaborative filtering algorithm with stylometric relevance feedback. Using the LitRec data set, we demonstrate that writing style influences book selection; that book content, characterized with writing style, can be used to improve collaborative filtering results; and that negative examples do not improve final predictions.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127044097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digitalkoot: electrifying the finnish cultural heritage","authors":"Ville Miettinen","doi":"10.1145/2064058.2064071","DOIUrl":"https://doi.org/10.1145/2064058.2064071","url":null,"abstract":"In this talk we present Digitalkoot, a system for correcting errors in Optical Character Recognition (OCR) processing of old text materials through the use of crowdsourcing. By turning the labor-intensive part into simple games, we have been able to attract a large crowd of tens of thousands of voluntary workers to donate their time for the cause.\u0000 Digitalkoot was created for the specific purpose of helping to digitize the newspaper archives of the National Library of Finland. We demonstrate how even untrained people can reach very high accuracy in a crowdsourced OCR process, and how we were able to overcome the design challenges related to attracting and managing a large pool of workers.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115502373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}