相关论文: Improving speaker de-identification with functiona…

This work investigates whether individuals can be identified solely through the pure dynamical components of their facial expressions, independent of static facial appearance. We leverage the FLAME 3D morphable model to achieve explicit…

The increasing use of cloud-based speech assistants has heightened the need for effective speech anonymization, which aims to obscure a speaker's identity while retaining critical information for subsequent tasks. One approach to achieving…

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…

Speaker embeddings extracted from voice recordings have been proven valuable for dementia detection. However, by their nature, these embeddings contain identifiable information which raises privacy concerns. In this work, we aim to…

In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the…

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 attack that generates…

Voice conversion (VC) aims to modify the speaker's identity while preserving the linguistic content. Commonly, VC methods use an encoder-decoder architecture, where disentangling the speaker's identity from linguistic information is…

Audio is a rich sensing modality that is useful for a variety of human activity recognition tasks. However, the ubiquitous nature of smartphones and smart speakers with always-on microphones has led to numerous privacy concerns and a lack…

The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications. These are essential since speech signals convey a wealth of rich, personal and…

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…

The scarcity of speaker-annotated far-field speech presents a significant challenge in developing high-performance far-field speaker verification (SV) systems. While data augmentation using large-scale near-field speech has been a common…

Data-intensive fine-tuning of speech foundation models (SFMs) to scarce and diverse dysarthric and elderly speech leads to data bias and poor generalization to unseen speakers. This paper proposes novel structured speaker-deficiency…

State-of-the-art approaches to speaker anonymization typically employ some form of perturbation function to conceal speaker information contained within an x-vector embedding, then resynthesize utterances in the voice of a new…

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and…

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In…

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that…