TeLearn - DigiCult

Information retrieval

Research projects targeting application areas such as digital libraries and archives are exploring methods and tools for (semi-)automatic indexing and semantic annotation of non-textual objects (music, speech, images). At the same time, they aim at enhancing information and knowledge retrieval through efficient search engines able to deliver results from complex multimedia resources, from distributed collections and across languages.

Examples for projects in this field are:

• CONTRAPUNCTUS - Preservation and unification of new and existing Braille Music digital sources for a new access methodology
  This project's goal was to enhance access to and use of musical scripts for blind musicians and musicologists. The results are an online portal as access point to a Braille score library, compiling files from the most important European libraries for the blind, an interactive music storage system with a range of innovative technical components, and a common XML-based format for Braille music data storage. In addition, the CONTRAPUNCTUS tools enable visually impaired users, through vocal, sound and tactile information, to explore and interact with the score.
  Fact sheet
• EASAIER - Enabling Access to Sound Archives through Integration, Enrichment and Retrieval
  EASAIER focussed on several key areas to improve access to sound archives: multi and cross- media retrieval, interactivity tools, integration of speech and music processing methods, and systemic archive analysis. The project developed innovative audio processing, data mining, and visualisation techniques, alongside user needs and evaluation studies, and integrated them into prototypes.
  Fact sheet
• ethnoarc - Linked European Archives for Ethnomusicological Research
  The EthnoArc system is enhancing access to scientific collections of traditional popular music by supporting digital representation, multi-archive retrieval and comparative research.
  Fact sheet
• IMAGINATION - Image-based Navigation in Multimedia Archives
  IMAGINATION proposes an automated method for capturing, indexing and semantic representation of non-textual objects to provide intuitive access and interaction through image embedded metadata. Major outcomes of the project will be a new and intuitive method of navigation through images and a set of technologies and tools to support the annotation of images by manual, semi-automatic and automatic techniques.
  Fact sheet
• MEMORIES - Design of an audio semantic indexation system allowing information retrieval for the access to archive content
  This project created a generic software library in order to facilitate the extraction of high level information from audio signals. The main innovations of the MEMORIES project are a user-friendly system that matches archivist needs for information retrieval in audio databases, the definition of a format for database structuring of information content descriptors and an efficient tool for audio restoration.
  Fact sheet
• MultiMATCH - Multilingual/Multimedia Access to Cultural Heritage
  MultiMATCH is a multilingual search engine specifically designed for access, organisation and personalised presentation of cultural heritage information of different formats (text, images, audio, video). The system is designed to support diverse user classes but also to assist cultural heritage institutions to disseminate their content widely and raise their visibility.
  Fact sheet
• PAPYRUS - Cultural and Historical Digital Libraries Dynamically Mined from News Archives
  PAPYRUS has created a cross-discipline digital library engine that allows for drawing content from one domain and making it available and understandable to the users of another.
  Fact sheet
• QVIZ - Query and context based visualization of time-spatial cultural dynamics)
  This project has created a collaborative time- and map-based environment for accessing digital archival resources. It allows searching archives without knowing the language of a record or the institution holding it, and can be enhanced through knowledge contributed by communities of practice.
  Fact sheet
• Treble-CLEF - Evaluation, Best Practice and Collaboration for Multilingual Information Access
  This Coordination Action has supported the development and consolidation of expertise in the research area multilingual information access. Another core activity was the dissemination of this know-how to the application communities in the digital libraries field.
  Fact sheet