Evaluation of algorithms for speaker diarization in sound recordings

Vanja Mileski (2015) Evaluation of algorithms for speaker diarization in sound recordings. EngD thesis.

Preview

Abstract

Speaker segmentation (diarisation, diarization) is a process that separates the audio clip in sections regarding the identity of the speakers. Speaker diarization in sound recordings answers the question of who spoke when? This thesis is dedicated to the automatic segmentation of speakers in a variety of sound recordings. We prepare a test data of audio recordings in Slovenian, which are obtained from field recordings. The recordings contain two or more speakers and very often they contain other sounds, silence, overlap between the speakers and the like. We manually build transcriptions for the number of speakers in them and the time interval of the speeches for each speaker which will represent our ground-truth. We run all the algorithms for diarization that we evaluate on this test data. We write a program which takes the results from the algorithms as an input which have different formats and different types of representation, and the results are converted to a common format. We evaluate the accuracy of the algorithms and analyse how well they work in different situations.

Item Type:

Thesis (EngD thesis)

Keywords:

speaker segmentation, diarization, diarisation, field recordings, speech, algorithm evaluation

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
doc. dr. Matija Marolt	271	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1536485827)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

3043

Date Deposited:

04 Sep 2015 16:13

Last Modified:

18 Sep 2015 13:16

URI:

http://eprints.fri.uni-lj.si/id/eprint/3043

Actions (login required)

View Item