Search Results for author: Ville Hautamäki

Found 26 papers, 13 papers with code

Meta-Learning Approaches for Improving Detection of Unseen Speech Deepfakes

no code implementations27 Oct 2024 Ivan Kukanov, Janne Laakkonen, Tomi Kinnunen, Ville Hautamäki

Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge.

DeepFake Detection Face Swapping +1

Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios

no code implementations25 Sep 2024 Marko Tuononen, Dani Korpi, Ville Hautamäki

We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model.

Behavioral Cloning via Search in Video PreTraining Latent Space

no code implementations27 Dec 2022 Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik

Our approach can effectively recover meaningful demonstration trajectories and show human-like behavior of an agent in the Minecraft environment.

Imitation Learning

Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs

no code implementations27 Oct 2022 Ruijie Tao, Kong Aik Lee, Rohan Kumar Das, Ville Hautamäki, Haizhou Li

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels.

Contrastive Learning Self-Supervised Learning +1

GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters

1 code implementation14 May 2022 Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki

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.

BIG-bench Machine Learning

The Transitive Information Theory and its Application to Deep Generative Models

no code implementations9 Mar 2022 Trung Ngo, Najwa Laabid, Ville Hautamäki, Merja Heinäniemi

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 disentangling representation but ultimately generating blurry examples.

Inductive Bias Variational Inference

Optimizing Tandem Speaker Verification and Anti-Spoofing Systems

no code implementations24 Jan 2022 Anssi Kanervisto, Ville Hautamäki, Tomi Kinnunen, Junichi Yamagishi

As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve security.

Speaker Verification

Improving Behavioural Cloning with Human-Driven Dynamic Dataset Augmentation

no code implementations19 Jan 2022 Federico Malato, Joona Jehkonen, Ville Hautamäki

Behavioural cloning has been extensively used to train agents and is recognized as a fast and solid approach to teach general behaviours based on expert trajectories.

Behavioural cloning

Distilling Reinforcement Learning Tricks for Video Games

1 code implementation1 Jul 2021 Anssi Kanervisto, Christian Scheller, Yanick Schraner, Ville Hautamäki

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains.

Q-Learning reinforcement-learning +2

Multi-task Learning with Attention for End-to-end Autonomous Driving

no code implementations21 Apr 2021 Keishi Ishihara, Anssi Kanervisto, Jun Miura, Ville Hautamäki

This does not only improve the success rate of standard benchmarks, but also the ability to react to traffic lights, which we show with standard benchmarks.

Autonomous Driving Imitation Learning +1

General Characterization of Agents by States they Visit

1 code implementation2 Dec 2020 Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki

Behavioural characterizations (BCs) of decision-making agents, or their policies, are used to study outcomes of training algorithms and as part of the algorithms themselves to encourage unique policies, match expert policy or restrict changes to policy per update.

Imitation Learning

Playing Minecraft with Behavioural Cloning

1 code implementation7 May 2020 Anssi Kanervisto, Janne Karttunen, Ville Hautamäki

MineRL 2019 competition challenged participants to train sample-efficient agents to play Minecraft, by using a dataset of human gameplay and a limit number of steps the environment.

Behavioural cloning

Action Space Shaping in Deep Reinforcement Learning

1 code implementation2 Apr 2020 Anssi Kanervisto, Christian Scheller, Ville Hautamäki

In this work, we aim to gain insight on these action space modifications by conducting extensive experiments in video-game environments.

reinforcement-learning Reinforcement Learning +1

Benchmarking End-to-End Behavioural Cloning on Video Games

1 code implementation2 Apr 2020 Anssi Kanervisto, Joonas Pussinen, Ville Hautamäki

We take a step towards a general approach and study the general applicability of behavioural cloning on twelve video games, including six modern video games (published after 2010), by using human demonstrations as training data.

Behavioural cloning Benchmarking +1

Towards Debugging Deep Neural Networks by Generating Speech Utterances

1 code implementation6 Jul 2019 Bilal Soomro, Anssi Kanervisto, Trung Ngo Trong, Ville Hautamäki

One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one of the classes.

General Classification Image Classification

SISUA: Semi-Supervised Generative Autoencoder for Single Cell Data

1 code implementation ICML Workshop on Computational Biology 2019 2019 Trung Ngo Trong, Roger Kramer, Juha Mehtonen, Gerardo González, Ville Hautamäki, Merja Heinäniemi

In this study, we propose models based on the Bayesian generative approach, where protein quantification available as CITE-seq counts from the same cells are used to constrain the learning process, thus forming a semi-supervised model.

Diversity Single-cell modeling

From Video Game to Real Robot: The Transfer between Action Spaces

1 code implementation2 May 2019 Janne Karttunen, Anssi Kanervisto, Ville Kyrki, Ville Hautamäki

Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training.

Reinforcement Learning Transfer Learning

Who Do I Sound Like? Showcasing Speaker Recognition Technology by YouTube Voice Search

1 code implementation8 Nov 2018 Ville Vestman, Bilal Soomro, Anssi Kanervisto, Ville Hautamäki, Tomi Kinnunen

The popularization of science can often be disregarded by scientists as it may be challenging to put highly sophisticated research into words that general public can understand.

Audio and Speech Processing Sound

ToriLLE: Learning Environment for Hand-to-Hand Combat

1 code implementation26 Jul 2018 Anssi Kanervisto, Ville Hautamäki

We present Toribash Learning Environment (ToriLLE), a learning environment for machine learning agents based on the video game Toribash.

BIG-bench Machine Learning

Staircase Network: structural language identification via hierarchical attentive units

no code implementations30 Apr 2018 Trung Ngo Trong, Ville Hautamäki, Kristiina Jokinen

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters.

General Classification Language Identification

Fantastic 4 system for NIST 2015 Language Recognition Evaluation

no code implementations5 Feb 2016 Kong Aik Lee, Ville Hautamäki, Anthony Larcher, Wei Rao, Hanwu Sun, Trung Hieu Nguyen, Guangsen Wang, Aleksandr Sizov, Ivan Kukanov, Amir Poorjam, Trung Ngo Trong, Xiong Xiao, Cheng-Lin Xu, Hai-Hua Xu, Bin Ma, Haizhou Li, Sylvain Meignier

This article describes the systems jointly submitted by Institute for Infocomm (I$^2$R), the Laboratoire d'Informatique de l'Universit\'e du Maine (LIUM), Nanyang Technology University (NTU) and the University of Eastern Finland (UEF) for 2015 NIST Language Recognition Evaluation (LRE).

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.