Zobrazeno 1 - 10
of 3 812
pro vyhledávání: '"Thébaud A"'
Autor:
Xinyuan, Henry Li, Joshi, Sonal, Thebaud, Thomas, Villalba, Jesus, Dehak, Najim, Khudanpur, Sanjeev
Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning attacks, whic
Externí odkaz:
http://arxiv.org/abs/2409.08985
Autor:
Thebaud, Thomas, Favaro, Anna, Chen, Casey, Chavez, Gabrielle, Moro-Velazquez, Laureano, Butala, Ankur, Dehak, Najim
Motor changes are early signs of neurodegenerative diseases (NDs) such as Parkinson's disease (PD) and Alzheimer's disease (AD), but are often difficult to detect, especially in the early stages. In this work, we examine the behavior of a wide array
Externí odkaz:
http://arxiv.org/abs/2409.08303
Biometric recognition systems are security systems based on intrinsic properties of their users, usually encoded in high dimension representations called embeddings, which potential theft would represent a greater threat than a temporary password or
Externí odkaz:
http://arxiv.org/abs/2408.08918
Publikováno v:
Applied Surface Science, 161076, 2024
Here, we compare the stabilities of different III-V crystals configurations on stepped Si substrates, with or without anti-phase boundaries, for abrupt and compensated interfaces, using density functional theory. Thermodynamic stability of the differ
Externí odkaz:
http://arxiv.org/abs/2406.09476
Autor:
Wang, Helin, Villalba, Jesus, Moro-Velazquez, Laureano, Hai, Jiarui, Thebaud, Thomas, Dehak, Najim
Speech separation, the task of isolating multiple speech sources from a mixed audio signal, remains challenging in noisy environments. In this paper, we propose a generative correction method to enhance the output of a discriminative separator. By le
Externí odkaz:
http://arxiv.org/abs/2406.07461
Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary classifier dis
Externí odkaz:
http://arxiv.org/abs/2402.19355
Autor:
Bhati, Saurabhchand, Villalba, Jesús, Moro-Velazquez, Laureano, Thebaud, Thomas, Dehak, Najim
Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to improve speech
Externí odkaz:
http://arxiv.org/abs/2309.04628
Controlling thermal transport in insulators and semiconductors is crucial for many technological fields such as thermoelectrics and thermal insulation, for which a low thermal conductivity ($\kappa$) is desirable. A major obstacle for realizing low $
Externí odkaz:
http://arxiv.org/abs/2308.10836
Autor:
Wang, Helin, Thebaud, Thomas, Villalba, Jesus, Sydnor, Myra, Lammers, Becky, Dehak, Najim, Moro-Velazquez, Laureano
We present a novel typical-to-atypical voice conversion approach (DuTa-VC), which (i) can be trained with nonparallel data (ii) first introduces diffusion probabilistic model (iii) preserves the target speaker identity (iv) is aware of the phoneme du
Externí odkaz:
http://arxiv.org/abs/2306.10588
Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self-FiLM to inject self-supervision into existing BWE models via Feature-wise Line
Externí odkaz:
http://arxiv.org/abs/2303.03657