Related papers: Protecting gender and identity with disentangled s…
In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on…
Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…
Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…
Over the last decade, the use of Automatic Speaker Verification (ASV) systems has become increasingly widespread in response to the growing need for secure and efficient identity verification methods. The voice data encompasses a wealth of…
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…
Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…
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…
We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance…
Existing privacy-preserving speech representation learning methods target a single application domain. In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its…
The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training data. In this study, we propose a speaker privacy-preserving…
Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…
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…
Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive…
Voice User Interfaces (VUIs) are increasingly popular and built into smartphones, home assistants, and Internet of Things (IoT) devices. Despite offering an always-on convenient user experience, VUIs raise new security and privacy concerns…
Self-supervised speaker embeddings are widely used in speaker verification systems, but prior work has shown that they often encode sensitive demographic attributes, raising fairness and privacy concerns. This paper investigates the extent…
Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…
Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such…
Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to transform a speech signal to remove the source speaker's…
Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…
Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encoded in orthogonal…