Speaker De-identification System using Autoencodersand Adversarial Training
The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice assistants empowered by the vertiginous breakthroughs in Deep Learning are prompting important concerns in the European Union to preserve speech data privacy. For instance, an attacker can record speech from users and impersonate them to get access to systems requiring voice identification. Hacking speaker profiles from users is also possible by means of existing technology to extract speaker, linguistic (e.g., dialect) and paralinguistic features (e.g., age) from the speech signal. In order to mitigate these weaknesses, in this paper, we propose a speaker de-identification system based on adversarial training and autoencoders in order to suppress speaker, gender, and accent information from speech. Experimental results show that combining adversarial learning and autoencoders increase the equal error rate of a speaker verification system while preserving the intelligibility of the anonymized spoken content.
Code (0)
등록된 구현이 없습니다.
Tasks
De-identificationSpeaker VerificationSimilar Papers 제목 키워드 기반
Symmetric Saliency-based Adversarial Attack To Speaker Identification
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based a…
Adversarial AttackDecoderSpeaker IdentificationFoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances
Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification. In this work, we propose a white-box steganography-inspired adversarial a…
Adversarial AttackSpeaker IdentificationTubes Among Us: Analog Attack on Automatic Speaker Identification
Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern syst…
BIG-bench Machine LearningSpeaker IdentificationAdversarial Speaker Verification
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, an…
General ClassificationSpeaker RecognitionSpeaker VerificationText-Dependent Speaker VerificationCosine similarity-based adversarial process
An adversarial process between two deep neural networks is a promising approach to train a robust model. In this paper, we propose an adversarial process using cosine similarity, whereas conventional adversarial processe…
Speaker Identification