Privacy-Preserving Speaker Recognition with Cohort Score Normalisation

Nautsch, Andreas; Patino, José; Treiber, Amos; Stafylakis, Themos; Mizera, Petr; Todisco, Massimiliano; Schneider, Thomas; Evans, Nicholas

doi:10.21437/interspeech.2019-2638

Cited by 5 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nautsch et al. [24] addressed the issue of computational overhead. They present a solution for computationally manageable privacy‐preserving speaker recognition with cohort score normalisation.…”

Section: Related Workmentioning

confidence: 99%

Privacy‐preserving speaker verification system based on binary I‐vectors

et al. 2021

View full text Add to dashboard Cite

Speaker verification is a key technology in many services and applications like smartphones and intelligent digital assistants. These applications usually require users to transmit their recordings, features, or models from their voices over untrusted public networks which stored and processed them on cloud-based infrastructure. Furthermore, the voice signal contains a great deal of the speaker's personal and private information which raises several privacy issues. Therefore, it is necessary to develop speaker verification systems that protect the user's voice against such threats. Herein, the cancellable biometric systems have been introduced as a privacy-preserving solution. A cancellable method for speaker verification systems is proposed using speaker i-vector embeddings. This method includes two stages: (i) i-vector binarisation and (ii) the protection of the binary i-vector with a shuffling scheme derived from a user-specific key. Privacy evaluation of this method according to the standards of biometric information protection (ISO/IEC 24745) shows that the proposed cancellable speaker verification system achieves the revocability, unlinkability, and irreversibility requirements. Moreover, the cancellable system improves biometric performance compared with the unprotected system and makes it resistant to different attack scenarios. Additionally, we demonstrate that this method can also operate to protect deep neural network speaker embeddings such as x-vectors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Related Workmentioning

confidence: 99%

Privacy‐preserving speaker verification system based on binary I‐vectors

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Several studies have attempted to tackle privacy protection in speech processing systems by extracting privacy-preserving features from speeches [6], [7], extracting features from encrypted signals [8], augmenting models with adversarial representations [9], and applying score normalizations [10]. However, such feature-or model-level privacy protection techniques have a critical drawback, wherein the users cannot verify that their personal information is actually removed from the resultant features or models.…”

Section: Introductionmentioning

confidence: 99%

Speaker Anonymization for Personal Information Protection Using Voice Conversion Techniques

et al. 2020

View full text Add to dashboard Cite

As speech-based user interfaces integrated in the devices such as AI speakers become ubiquitous, a large amount of user voice data is being collected to enhance the accuracy of speech recognition systems. Since such voice data contain personal information that can endanger the privacy of users, the issue of privacy protection in the speech data has garnered increasing attention after the introduction of the General Data Protection Regulation in the EU, which implies that restrictions and safety measures for the use of speech data become essential. This study aims to filter the speaker-related voice biometrics present in speech data such as voice fingerprint without altering the linguistic content to preserve the usefulness of the data while protecting the privacy of users. To achieve this, we propose an algorithm that produces anonymized speeches by adopting many-to-many voice conversion techniques based on variational autoencoders (VAEs) and modifying the speaker identity vectors of the VAE input to anonymize the speech data. We validated the effectiveness of the proposed method by measuring the speaker-related information and the original linguistic information retained in the resultant speech, using an open source speaker recognizer and a deep neural network-based automatic speech recognizer, respectively. Using the proposed method, the speaker identification accuracy of the speech data was reduced to 0.1-9.2%, indicating successful anonymization, while the speech recognition accuracy was maintained as 78.2-81.3%.

show abstract