<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Two basic tasks are covered in this paper. The first one consists in the design and practical testing of a new method for voice de-identification that changes the apparent age and/or gender of a speaker by multi-segmental frequency scale transformation combined with prosody modification. The second task is aimed at verification of applicability of a classifier based on Gaussian mixture models (GMM) to detect the original Czech and Slovak speakers after applied voice deidentification. The performed experiments confirm functionality of the developed gender and age conversion for all selected types of de-identification which can be objectively evaluated by the GMM-based open-set classifier. The original speaker detection accuracy was compared also for sentences uttered by German and English speakers showing language independence of the proposed method.</p></abstract>

Two basic tasks are covered in this paper. The first one consists in the design and practical testing of a new method for voice de-identification that changes the apparent age and/or gender of a speaker by multi-segmental frequency scale transformation combined with prosody modification. The second task is aimed at verification of applicability of a classifier based on Gaussian mixture models (GMM) to detect the original Czech and Slovak speakers after applied voice deidentification. The performed experiments confirm functionality of the developed gender and age conversion for all selected types of de-identification which can be objectively evaluated by the GMM-based open-set classifier. The original speaker detection accuracy was compared also for sentences uttered by German and English speakers showing language independence of the proposed method.

Evaluation of speaker de-identification based on voice gender and age conversion

Institute of Measurement Science, Slovak Academy of Sciences

Slovak University of Technology in Bratislava

Faculty of Electrical Engineering and Information Technology

Department of Cybernetics, Faculty of Applied Sciences

Journal of Electrical Engineering

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Evaluation of speaker de-identification based on voice gender and age conversion"}

Two basic tasks are covered in this paper. The first one consists in the design and practical testing of a new method for voice de-identification that changes...

Evaluation of speaker de-identification based on voice gender and age conversion

Online veröffentlicht: 30. Mai 2018

Seitenbereich: 138 - 147

Eingereicht: 14. Nov. 2017

DOI: https://doi.org/10.2478/jee-2018-0017

Schlüsselwörter
GMM classifier, spectral and prosodic features of speech, speaker gender and age classification

© 2018 Jiří Přibil et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Evaluation of speaker de-identification based on voice gender and age conversion

Online veröffentlicht: 30. Mai 2018

Seitenbereich: 138 - 147

Eingereicht: 14. Nov. 2017

DOI: https://doi.org/10.2478/jee-2018-0017

SchlüsselwörterGMM classifier, spectral and prosodic features of speech, speaker gender and age classification

© 2018 Jiří Přibil et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Schlüsselwörter
GMM classifier, spectral and prosodic features of speech, speaker gender and age classification