Related papers: Pinhole Effect on Linkability and Dispersion in Sp…

Recordings in everyday life require privacy preservation of the speech content and speaker identity. This contribution explores the influence of noise and reverberation on the trade-off between privacy and utility for low-cost…

Speaker identity plays a significant role in human communication and is being increasingly used in societal applications, many through advances in machine learning. Speaker identity perception is an essential cognitive phenomenon that can…

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…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

While audio recordings in real life provide insights into social dynamics and conversational behavior, they also raise concerns about the privacy of personal, sensitive data. This article explores the effectiveness of restricting recordings…

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

We introduce a system capable of faithfully modifying the perceptual voice quality of creak while preserving the speaker's perceived identity. While it is well known that high creak probability is typically correlated with low pitch, it is…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Due to a constantly increasing amount of speech data that is stored in different types of databases, voice privacy has become a major concern. To respond to such concern, speech researchers have developed various methods for speaker…

Voice conversion for speaker anonymization is an emerging field in speech processing research. Many state-of-the-art approaches are based on the resynthesis of the phoneme posteriorgrams (PPG), the fundamental frequency (F0) of the input…

This study focuses on the First VoicePrivacy Attacker Challenge within the ICASSP 2025 Signal Processing Grand Challenge, which aims to develop speaker verification systems capable of determining whether two anonymized speech signals are…

Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Facilitated by the speech generation framework that disentangles speech into content, speaker, and prosody, voice anonymization is accomplished by substituting the original speaker embedding vector with that of a pseudo-speaker. In this…

Voice anonymisation aims to conceal the voice identity of speakers in speech recordings. Privacy protection is usually estimated from the difficulty of using a speaker verification system to re-identify the speaker post-anonymisation.…

Because the performance of speech separation is excellent for speech in which two speakers completely overlap, research attention has been shifted to dealing with more realistic scenarios. However, domain mismatch between training/test…

We investigate the effect of speaker localization on the performance of speech recognition systems in a multispeaker, multichannel environment. Given the speaker location information, speech separation is performed in three stages. In the…

In the scenario of the Voice Privacy challenge, anonymization is achieved by converting all utterances from a source speaker to match the same target identity; this identity being randomly selected. In this context, an attacker with maximum…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Human speech conveys prosody, linguistic content, and speaker identity. This article investigates a novel speaker anonymization approach using an end-to-end network based on a Vector-Quantized Variational Auto-Encoder (VQ-VAE) to deal with…