Change search
ReferencesLink to record
Permanent link

Direct link
Development of a Speaker Recognition Solution in Vidispine
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2013 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

A video database contains an enormous amount of information. In order to search through the database, metadata can be attached to each video. One such type of metadata can be labels containing speakers and where they are speaking. With the help of speaker recognition this type of metadata can automatically be assigned to each video. In this thesis a speaker recognition plug-in for Vidispine, an API media asset management platform, is presented. The plug-in was developed with the help of the LIUM SpkDiarization toolkit for speaker diarization and the ALIZE/LIA RAL toolkit for speaker identification.

The choice of using the method of GMM-UBM that ALIZE/LIA RAL offers, was made through an in-depth theoretical study of different identification methods. The in-depth study is presented in its own chapter. The goal of the plug-in was to perform an identification rate of 85%. However, the results unfortunately became as low as 63%. Among the issues the plug-in faces, its low performance on female speaker was shown to be crucial.

Place, publisher, year, edition, pages
, UMNAD, 943
National Category
Engineering and Technology
URN: urn:nbn:se:umu:diva-74180OAI: diva2:633539
External cooperation
CodeMill AB
Educational program
Master's Programme in Computing Science
Available from: 2013-06-27 Created: 2013-06-27 Last updated: 2013-06-27Bibliographically approved

Open Access in DiVA

fulltext(1838 kB)273 downloads
File information
File name FULLTEXT01.pdfFile size 1838 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Department of Computing Science
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 273 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 217 hits
ReferencesLink to record
Permanent link

Direct link