@phdthesis{Akermark2017,
  type      = {Master Thesis},
  author    = {Gunnar {\AA}kermark},
  title     = {Workflow for Automatic i-Vector based Speaker Identification on German Parliament Speakers},
  institution = {Fraunhofer Publica},
  doi       = {10.24406/publica-fhg-281487},
  pages     = {VI, 53},
  year      = {2017},
  abstract  = {In order to help journalists investigate inside large audiovisual archives, as maintained by news broadcast agencies, the multimedia data must be indexed by text-based search engies. By automatically creating a transcript through automatic speech recognition (ASR), the spoken word becomes accessible to text search, and queries for keywords are made possible. But stil, important contextual information like the identity of the speaker is not captured. Especially when gathering original footage in the political domain, the identity of the speaker can be the most important query constraint, although this name may not be prominent in the words spoken. It is thus desireable to have this information provided explicitely to the search engine. To provide this information, the archive must be an alyzed by automatic Speaker Identification (SID). While this research topic has seen substantial gains in accuracy and robustness over last years, it has not yet established itself as a helpful, large-scale tool outside the research community. This thesis sets out to establish a workflow to provide automatic speaker identification. Its application is to help journalists searching on speeches given in the German parliament (Bundestag). This is a contribution to the News-Stream 3.0 project, a BMBF funded research project that addresses accessibility of various data sources for journalists.},
  language  = {en}
}