Privacy-oriented manipulation of speaker representations
원문 초록
Speaker embeddings are ubiquitous, with applications ranging from speaker recognition and diarization to speech synthesis and voice anonymisation. The amount of information held by these embeddings lends them versatility, but also raises privacy concerns. Speaker embeddings have been shown to contain information on age, sex, health and more, which speakers may want to keep private, especially when this information is not required for the target task. In this work, we propose a method for removing and manipulating private attributes from speaker embeddings that leverages a Vector-Quantized Variational Autoencoder architecture, combined with an adversarial classifier and a novel mutual information loss. We validate our model on two attributes, sex and age, and perform experiments with ignorant and fully-informed attackers, and with in-domain and out-of-domain data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VoxSim: A perceptual voice similarity dataset
Text-To-Speech Synthesis In The Wild
Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning
Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
We Need Variations in Speech Generation: Sub-center Modelling for Speaker Embeddings
DeepGesture: A conversational gesture synthesis system based on emotions and semantics
토론
이 논문과 연결된 포럼 글이 아직 없습니다.