Matias Pizarro

According to our database, Matias Pizarro authored at least 7 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks.

Matías P. Pizarro B., Raghavan Narasimhan, Asja Fischer

CoRR, March, 2026

Comparative study on noise-augmented training and its effect on adversarial robustness in ASR systems.

Karla Pizzi, Matias Pizarro, Asja Fischer

Comput. Speech Lang., 2026

2024

Single-Model Attribution for Spoofed Speech via Vocoder Fingerprints in an Open-World Setting.

Matias Pizarro, Mike Laszkiewicz, Dorothea Kolossa, Asja Fischer

CoRR, 2024

Reassessing Noise Augmentation Methods in the Context of Adversarial Speech.

Karla Pizzi, Matías P. Pizarro B., Asja Fischer

CoRR, 2024

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution.

Matías P. Pizarro B., Dorothea Kolossa, Asja Fischer

Proceedings of the Uncertainty in Artificial Intelligence, 2024

2023

Leveraging characteristics of the output probability distribution for identifying adversarial audio examples.

Matías P. Pizarro B., Dorothea Kolossa, Asja Fischer

CoRR, 2023

2021

Robustifying automatic speech recognition by extracting slowly varying features.

Matias Pizarro, Dorothea Kolossa, Asja Fischer

CoRR, 2021