Speech de-identification with deep neural networks

Fodor Ádám and Kopácsi László and Milacski Zoltán Ádám and Lőrincz András: Speech de-identification with deep neural networks. In: Acta cybernetica, (25) 2. pp. 257-269. (2021)

[thumbnail of cybernetica_025_numb_002_257-269.pdf] Cikk, tanulmány, mű

Download (275kB)


Cloud-based speech services are powerful practical tools but the privacy of the speakers raises important legal concerns when exposed to the Internet. We propose a deep neural network solution that removes personal characteristics from human speech by converting it to the voice of a Text-to-Speech (TTS) system before sending the utterance to the cloud. The network learns to transcode sequences of vocoder parameters, delta and delta-delta features of human speech to those of the TTS engine. We evaluated several TTS systems, vocoders and audio alignment techniques. We measured the performance of our method by (i) comparing the result of speech recognition on the de-identified utterances with the original texts, (ii) computing the Mel-Cepstral Distortion of the aligned TTS and the transcoded sequences, and (iii) questioning human participants in A-not-B, 2AFC and 6AFC tasks. Our approach achieves the level required by diverse applications.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2021
Volume: 25
Number: 2
ISSN: 0324-721X
Page Range: pp. 257-269
Language: English
Publisher: University of Szeged, Institute of Informatics
Place of Publication: Szeged
Event Title: Conference of PhD Students in Computer Science (12.) (2020) (Szeged)
Related URLs: http://acta.bibl.u-szeged.hu/75565/
DOI: 10.14232/actacyb.288282
Uncontrolled Keywords: Beszédfeldolgozás, Adatvédelem, Programozás
Additional Information: Bibliogr.: p. 266-269. ; ill. ; összefoglalás angol nyelven
Subjects: 01. Natural sciences
01. Natural sciences > 01.02. Computer and information sciences
Date Deposited: 2022. May. 12. 14:44
Last Modified: 2022. May. 12. 14:44
URI: http://acta.bibl.u-szeged.hu/id/eprint/75609

Actions (login required)

View Item View Item