Background and activities
MSc Computer Science (NTNU). PhD candidate in the MEGAS project (Metadata generation for auto-transcribed speech) which is part of SCRIBE (Machine transcription of Norwegian conversational speech), a collaboration between NTNU, NRK, the National Library of Norway and Telenor.
The working title for the thesis:
Summarization and metadata generation for transcribed broadcast media
The work is foucsed towards uncovering and improving upon available techniques for enriching information in radio, podcasts and TV captions, mainly focused towards aiding the hearing impaired. Focus areas include data manipulation from automatic speech recognition systems, metadata generation and summarization
Scientific, academic and artistic work
A selection of recent journal publications, artistic productions, books, including book and report excerpts. See all publications in the database
- (2020) Augmenting Entity-level Sentiment Analysis with Coreference Resolution. 2020.