Zobrazeno 1 - 10
of 91
pro vyhledávání: '"Hautamäki, Ville"'
Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferation of speech deepfakes on social media underscores the need for systems
Externí odkaz:
http://arxiv.org/abs/2410.20578
Autor:
Tuononen, Marko, Hautamäki, Ville
Mutual information provides a powerful, general-purpose metric for quantifying the amount of shared information between variables. Estimating normalized mutual information using a k-Nearest Neighbor (k-NN) based approach involves the calculation of t
Externí odkaz:
http://arxiv.org/abs/2410.07642
We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of th
Externí odkaz:
http://arxiv.org/abs/2409.16768
We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level instructions into m
Externí odkaz:
http://arxiv.org/abs/2403.13801
Speaker verification is hampered by background noise, particularly at extremely low Signal-to-Noise Ratio (SNR) under 0 dB. It is difficult to suppress noise without introducing unwanted artifacts, which adversely affects speaker verification. We pro
Externí odkaz:
http://arxiv.org/abs/2401.02626
Autor:
Milani, Stephanie, Kanervisto, Anssi, Ramanauskas, Karolis, Schulhoff, Sander, Houghton, Brandon, Mohanty, Sharada, Galbraith, Byron, Chen, Ke, Song, Yan, Zhou, Tianze, Yu, Bingquan, Liu, He, Guan, Kai, Hu, Yujing, Lv, Tangjie, Malato, Federico, Leopold, Florian, Raut, Amogh, Hautamäki, Ville, Melnik, Andrew, Ishida, Shu, Henriques, João F., Klassert, Robert, Laurito, Walter, Novoseller, Ellen, Goecks, Vinicius G., Waytowich, Nicholas, Watkins, David, Miller, Josh, Shah, Rohin
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms t
Externí odkaz:
http://arxiv.org/abs/2303.13512
Our aim is to build autonomous agents that can solve tasks in environments like Minecraft. To do so, we used an imitation learning-based approach. We formulate our control problem as a search problem over a dataset of experts' demonstrations, where t
Externí odkaz:
http://arxiv.org/abs/2212.13326
We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance of various
Externí odkaz:
http://arxiv.org/abs/2210.15385
Playing games with cheaters is not fun, and in a multi-billion-dollar video game industry with hundreds of millions of players, game developers aim to improve the security and, consequently, the user experience of their games by preventing cheating.
Externí odkaz:
http://arxiv.org/abs/2205.07060
Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient for disent
Externí odkaz:
http://arxiv.org/abs/2203.05074