PhD Student
Research Interests
- Detecting and preventing adversarial attacks on ASR systems.
- Identifying fake vs. genuine audio with machine learning.
- Improving the robustness and reliability of audio-based systems.
Teaching
Publications
2024
Artikel
Single-Model Attribution for Spoofed Speech via Vocoder Fingerprints in an Open-World Setting
Matías Pizarro, Mike Laszkiewicz, Dorothea Kolossa, Asja Fischer
In: arXiv Preprint, 2024.
@article{Pizarro2024Vocoder,
title = {Single-Model Attribution for Spoofed Speech via Vocoder Fingerprints in an Open-World Setting},
author = {Matías Pizarro and Mike Laszkiewicz and Dorothea Kolossa and Asja Fischer},
url = {https://arxiv.org/abs/2411.14013},
year = {2024},
date = {2024-01-01},
journal = {arXiv Preprint},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Proceedings Article
Reassessing Noise Augmentation Methods in the Context of Adversarial Speech
Karla Pizzi, Matías Pizarro, Asja Fischer
In: Symposium on Security and Privacy in Speech Communication (SPSC), 2024.
@inproceedings{Pizzi2024NoiseAugmentation,
title = {Reassessing Noise Augmentation Methods in the Context of Adversarial Speech},
author = {Karla Pizzi and Matías Pizarro and Asja Fischer},
url = {https://arxiv.org/abs/2409.01813},
doi = {10.21437/SPSC.2024-5},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Symposium on Security and Privacy in Speech Communication (SPSC)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Proceedings Article
DistriBlock: Identifying Adversarial Audio Samples by Leveraging Characteristics of the Output Distribution
Matías Pizarro, Dorothea Kolossa, Asja Fischer
In: Conference on Uncertainty in Artificial Intelligence (UAI), 2024.
@inproceedings{Pizarro2024DistriBlock,
title = {DistriBlock: Identifying Adversarial Audio Samples by Leveraging Characteristics of the Output Distribution},
author = {Matías Pizarro and Dorothea Kolossa and Asja Fischer},
url = {https://proceedings.mlr.press/v244/pizarro24a.html
https://arxiv.org/abs/2305.17000},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2021
Proceedings Article
Robustifying Automatic Speech Recognition by Extracting Slowly Varying Features
Matías Pizarro, Dorothea Kolossa, Asja Fischer
In: Symposium on Security and Privacy in Speech Communication (SPSC), 2021.
@inproceedings{Pizarro2021SlowFeatures,
title = {Robustifying Automatic Speech Recognition by Extracting Slowly Varying Features},
author = {Matías Pizarro and Dorothea Kolossa and Asja Fischer},
url = {https://arxiv.org/abs/2112.07400},
doi = {10.21437/SPSC.2021-8},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Symposium on Security and Privacy in Speech Communication (SPSC)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}