Language and multimedia: analysis, retrieval and interaction

bosnian-memories

Bosnian Memories

In this project,100 citizens of Bosnia and Herzegovina (BiH) from various social layers and regions have been interviewed with a video camera about their personal experiences during the Second World War and the recent war between 1991 and 1995. The recordings are made available to the public through an online interview platform that is freely accessible and can be searched with a broad variety of keywords. Subtitles in the local language and in English are available. ... read more

video interview croatian woman, she has her hand on her hea

Croatian Memories

The aim of the project Unveiling personal memories on war and detention is to affirm personal memories of all interested witnesses of political events in Croatia and to preserve them from falling into oblivion. We have recorded more than 400 video interviews. A large part of the video materials has been transcribed, translated and made available in the video archives of this web site, while a part of the interviews is available only for research in Documenta. ... read more

Buchenwald demonstrator

The Buchenwald demonstrator supports access to and search interviews with Buchenwald survivors. The demonstrator linked to a website set up in collaboration with NIOD. ... read more

Radio Oranje demonstrator

Met behulp van deze demonstrator kunt u zoeken in de toespraken van H.M. Koningin Wilhelmina die tijdens de Tweede Wereldoorlog door Radio Oranje zijn uitgezonden. ... read more

Broadcast News Demonstrator

This showcase demonstrates searching/browsing in Audio and Video-content of NOS 8 o'clock journal using multimedia retrieval technology. Two options can be used:
- The classical way: in journal of the last 4 weeks, using Teletext subtitles, or using the audio (which is transferred to text) using a Dutch speech-recognizer. All work is done automatically: the video-file is cut automatically in segments based on changing the item (teletext) or changing the speaker (speech-recognition).
- Using Google Maps you can browse through the 8 o'clock journal of the latest 4 weeks. Places are found in the teletext or subtitles information. ... read more

Twente News Corpus

The development of the corpus started in 1998 within a predecessor project DRUID and has a size of more then 500M words. The text part has been built from texts of four different sources:
- Dutch national newspapers;
- Television subtitles;
- Teleprompter (auto-cues) files;
- Both manually and automatically generated broadcast news transcripts along with the broadcast news audio.
. ... read more