Work

Privacy-preserving sound to degrade automatic speaker verification performance

Year: 2016

Type: conference-paper

Abstract: In this paper, a privacy protection method to prevent speaker identification from recorded speech is proposed and evaluated. Although many techniques for preserving various private information included in speech have been proposed, their impacts on human speech communication in physical space are not taken into account. To overcome this problem, this paper proposes privacy-preserving sound as a privacy protection method. The privacy-preserving sound can degrade speaker verification performance without interfering with human speech communication in physical space. To make a first step toward solving this problem, suitable sound characteristics for preserving privacy are evaluated in terms of the speaker verification performance and speech intelligibility. The experimental results show that appropriate sound can efficiently degrade the speaker verification performance without degrading speech intelligibility.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp.2016.7472729

Authors: Kei Hashimoto, Junichi Yamagishi, Isao Echizen

Institutions: Nagoya Institute of Technology, National Institute of Informatics, University of Edinburgh

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2407075323

FWCI: 0.718

Cites: 19

Cited by: 30

Related to: 10