Related papers: SecureSpeech: Prompt-based Speaker and Content Pro…

Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference…

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the…

Voice anonymization masks vocal traits while preserving linguistic content, which may still leak speaker-specific patterns. To assess and strengthen privacy evaluation, we propose a dual-stream attacker that fuses spectral and…

With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models…

Lip-to-speech synthesis aims to generate speech audio directly from silent facial video by reconstructing linguistic content from lip movements, providing valuable applications in situations where audio signals are unavailable or degraded.…

Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearning is insufficient in this context, as zero-shot TTS can…

Recent strides in neural speech synthesis technologies, while enjoying widespread applications, have nonetheless introduced a series of challenges, spurring interest in the defence against the threat of misuse and abuse. Notably, source…

In our previous work, we proposed a language-independent speaker anonymization system based on self-supervised learning models. Although the system can anonymize speech data of any language, the anonymization was imperfect, and the speech…

Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural…

The rising trend of using voice as a means of interacting with smart devices has sparked worries over the protection of users' privacy and data security. These concerns have become more pressing, especially after the European Union's…

Recent advances in scene-based video generation enable coherent visual narratives from structured prompts, yet a key aspect of storytelling -- character-driven dialogue and speech -- remains underexplored. We present a modular pipeline that…

Various techniques need to be combined to realize anonymously authenticated communication. Cryptographic tools enable anonymous user authentication while anonymous communication protocols hide users' IP addresses from service providers. One…

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…

In recent years, prompting has quickly become one of the standard ways of steering the outputs of generative machine learning models, due to its intuitive use of natural language. In this work, we propose a system conditioned on embeddings…

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a…

Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in…

Using our voices to access, and interact with, online services raises concerns about the trade-offs between convenience, privacy, and security. The conflict between maintaining privacy and ensuring input authenticity has often been hindered…

Smart devices serviced by large-scale AI models necessitates user data transfer to the cloud for inference. For speech applications, this means transferring private user information, e.g., speaker identity. Our paper proposes a…

As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data. A significant subset of these approaches incorporate differentially private…