Picture for Sarina Meyer

Sarina Meyer

The VoicePrivacy 2024 Challenge Evaluation Plan

Add code
Apr 03, 2024
Viaarxiv icon

Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions

Oct 26, 2023
Viaarxiv icon

The IMS Toucan System for the Blizzard Challenge 2023

Add code
Oct 26, 2023
Viaarxiv icon

VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research

Add code
Sep 14, 2023
Figure 1 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 2 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 3 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 4 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Viaarxiv icon

Modeling Speaker-Listener Interaction for Backchannel Prediction

Apr 10, 2023
Figure 1 for Modeling Speaker-Listener Interaction for Backchannel Prediction
Figure 2 for Modeling Speaker-Listener Interaction for Backchannel Prediction
Figure 3 for Modeling Speaker-Listener Interaction for Backchannel Prediction
Figure 4 for Modeling Speaker-Listener Interaction for Backchannel Prediction
Viaarxiv icon

Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy

Add code
Oct 20, 2022
Figure 1 for Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy
Figure 2 for Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy
Figure 3 for Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy
Figure 4 for Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy
Viaarxiv icon

Speaker Anonymization with Phonetic Intermediate Representations

Add code
Jul 11, 2022
Figure 1 for Speaker Anonymization with Phonetic Intermediate Representations
Figure 2 for Speaker Anonymization with Phonetic Intermediate Representations
Figure 3 for Speaker Anonymization with Phonetic Intermediate Representations
Figure 4 for Speaker Anonymization with Phonetic Intermediate Representations
Viaarxiv icon