3 papers
eess.AS2026
Revisiting Vocos: That Phasiness Business in Time-Frequency Neural Vocoding
Ãnal Ege GaznepoÄlu, 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…
eess.AS2026
You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Ãnal 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…
eess.AS2025
Why disentanglement-based speaker anonymization systems fail at preserving emotions?
Ãnal Ege Gaznepoglu, Nils Peters
Disentanglement-based speaker anonymization involves decomposing speech into a semantically meaningful representation, altering the speaker embedding, and resynthesizing a waveform…