4 papers · 1 filter
Revisiting Vocos: That Phasiness Business in Time-Frequency Neural Vocoding
Ünal Ege Gaznepoğlu, Frank Zalkow, Mohammad Joshaghani +3
Recently, time-frequency neural vocoders have been approaching the state-of-the-art quality of time-domain neural vocoders. Vocos is a notable example due to its efficiency, but it…
You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Ünal Ege Gaznepoglu, Anna Leschanowsky, Ahmad Aloradi +4
Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks…
Why disentanglement-based speaker anonymization systems fail at preserving emotions?
Ünal Ege Gaznepoglu, Nils Peters
Disentanglement-based speaker anonymization involves decomposing speech into a semantically meaningful representation, altering the speaker embedding, and resynthesizing a waveform…
Voice Anonymization for All -- Bias Evaluation of the Voice Privacy Challenge Baseline System
Anna Leschanowsky, Ünal Ege Gaznepoglu, Nils Peters
In an age of voice-enabled technology, voice anonymization offers a solution to protect people's privacy, provided these systems work equally well across subgroups. This study inve…