Publications
Detail of publication
Citation
p. 411-418, Springer, 2016. : Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech . Speech and Computer 18th International Conference, SPECOM 2016,
Download PDF
Abstract
The goal of this paper is to evaluate the contribution of speaker change detection (SCD) to the performance of a speaker diarization system in the telephone domain. We compare the overall performance of an i-vector based system using both SCD-based segmentation and a naive constant length segmentation with overlapping segments. The diarization system performs K-means clustering of i-vectors which represent the individual segments, followed by a resegmentation step. Experiments were done on the English part of the CallHome corpus. The final results indicate that the use of speaker change detection is beneficial, but the differences between the two segmentation approaches are diminished by the use of resegmentation.
Detail of publication
Title: | Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech |
---|---|
Author: | Zbyněk Zajíc ; Marie Kunešová ; Vlasta Radová |
Language: | English |
Date of publication: | 23 Aug 2016 |
Year: | 2016 |
Type of publication: | Papers in proceedings of reviewed conferences |
Title of journal or book: | Speech and Computer 18th International Conference, SPECOM 2016 |
Page: | 411 - 418 |
ISBN: | 978-3-319-43957-0 |
Publisher: | Springer |
Keywords
speaker diarization, speaker change detection, i-vector, segmentation
BibTeX
@INPROCEEDINGS{ZbynekZajic_2016_Investigationof, author = {Zbyn\v{e}k Zaj\'{i}c and Marie Kune\v{s}ov\'{a} and Vlasta Radov\'{a}}, title = {Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech}, year = {2016}, publisher = {Springer}, journal = {Speech and Computer 18th International Conference, SPECOM 2016}, pages = {411-418}, ISBN = {978-3-319-43957-0}, url = {http://www.kky.zcu.cz/en/publications/ZbynekZajic_2016_Investigationof}, }