Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-9716
For citation please use:
Main Title: Speaker Identification for Swiss German with Spectral and Rhythm Features
Author(s): Lykartsis, Athanasios
Weinzierl, Stefan
Dellwo, Volker
Type: Conference Object
Is Part Of: 10.14279/depositonce-9530
Language Code: en
Abstract: We present results of speech rhythm analysis for automatic speaker identification. We expand previous experiments using similar methods for language identification. Features describing the rhythmic properties of salient changes in signal components are extracted and used in an speaker identification task to determine to which extent they are descriptive of speaker variability. We also test the performance of state-of-the-art but simple-to-extract frame-based features. The paper focus is the evaluation on one corpus (swiss german, TEVOID) using support vector machines. Results suggest that the general spectral features can provide very good performance on this dataset, whereas the rhythm features are not as successful in the task, indicating either the lack of suitability for this task or the dataset specificity.
URI: https://depositonce.tu-berlin.de/handle/11303/10821
http://dx.doi.org/10.14279/depositonce-9716
Issue Date: 13-Jun-2017
Date Available: 24-Feb-2020
DDC Class: 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
780 Musik
Subject(s): speech rhythm
speaker identification
language identification
beat histogram
swiss german
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: 2017 AES International Conference on Semantic Audio
Publisher: Audio Engineering Society
Publisher Place: New York, NY
Article Number: 2-1
Appears in Collections:FG Audiokommunikation » Publications

Files in This Item:
lykartsis_etal_2017.pdf
Format: Adobe PDF | Size: 622.04 kB
DownloadShow Preview
Thumbnail

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.