Publications
Detail of publication
Citation
p. 109-112, Academy of sciences of the Czech Republic, Prague, 2004. : A method for speaker-based segmentation of audio signals . Speech processing,
Download PDF
Abstract
The paper deals with the problem of speaker-based segmentation. The goal of this task is to extract homogeneous segments containing the longest possible utterances produced by a single speaker. In the method presented here, no assumption is made about prior knowledge of the speaker or speech signal characteristics (there is no speaker model, no speech model, even the number of speakers in the recording is not known).
Detail of publication
Title: | A method for speaker-based segmentation of audio signals |
---|---|
Author: | Zochová, P. ; Radová, V. |
Language: | English |
Date of publication: | 15 Sep 2003 |
Year: | 2004 |
Type of publication: | Papers in proceedings of reviewed conferences |
Title of journal or book: | Speech processing |
Page: | 109 - 112 |
ISBN: | 80-86269-10-8 |
Publisher: | Academy of sciences of the Czech Republic |
Address: | Prague |
Date: | 15 Sep 2003 - 17 Sep 2003 |
Keywords
speaker-based segmentation, Bayesian Information Criterion, detection of speaker turn
BibTeX
@INPROCEEDINGS{ZochovaP_2004_Amethodfor, author = {Zochov\'{a}, P. and Radov\'{a}, V.}, title = {A method for speaker-based segmentation of audio signals}, year = {2004}, publisher = {Academy of sciences of the Czech Republic}, journal = {Speech processing}, address = {Prague}, pages = {109-112}, ISBN = {80-86269-10-8}, url = {http://www.kky.zcu.cz/en/publications/ZochovaP_2004_Amethodfor}, }