18 citations · 51 across the 22 of their papers we have counts for
27 papers
NMINE: Normalized Mutual Information Neural Estimation
Petra Eerikinharju, Marko Tuononen, Ville Hautamäki
Mutual information is a general measure of statistical dependence that captures both linear and nonlinear relationships between random variables. For continuous and multidimensiona…
How Meta-Learning Shapes LoRA Adapter Geometry in Speech Deepfake Detection
Ivan Kukanov, Janne Laakkonen, Ville Hautamäki
Meta-learning for domain generalization (MLDG) improves out-of-distribution speech deepfake detection over empirical risk minimization (ERM) when both objectives train low-rank ada…
Zero-Shot Heart Rate Variability Forecasting from Consumer Wearables Using Time Series Foundation Models
Luukas Peräkylä, Fahad Sohrab, Ville Hautamäki +3
Short-term Heart Rate Variability (HRV) forecasting could provide clinicians with actionable lead time for detecting autonomic dysfunction and adverse cardiac events. Consumer wear…
Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
Xi Xuan, Wenxin Zhang, Zhiyu Li +3
Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting so…
Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence
Edem Ahadzi, Vishwanath Pratap Singh, Tomi Kinnunen +1
In this work, we present the first study addressing automatic speech recognition (ASR) for children in an online learning setting. This is particularly important for both child-cen…
Meta-Learning Approaches for Improving Detection of Unseen Speech Deepfakes
Ivan Kukanov, Janne Laakkonen, Tomi Kinnunen +1
Current speech deepfake detection approaches perform satisfactorily against known adversaries; however, generalization to unseen attacks remains an open challenge. The proliferatio…
Zero-shot Imitation Policy via Search in Demonstration Dataset
Federco Malato, Florian Leopold, Andrew Melnik +1
Behavioral cloning uses a dataset of demonstrations to learn a policy. To overcome computationally expensive training procedures and address the policy adaptation problem, we propo…
Gradient weighting for speaker verification in extremely low Signal-to-Noise Ratio
Yi Ma, Kong Aik Lee, Ville Hautamäki +2
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 un…
Behavioral Cloning via Search in Embedded Demonstration Dataset
Federico Malato, Florian Leopold, Ville Hautamaki +1
Behavioural cloning uses a dataset of demonstrations to learn a behavioural policy. To overcome various learning and policy adaptation problems, we propose to use latent space to i…
Behavioral Cloning via Search in Video PreTraining Latent Space
Federico Malato, Florian Leopold, Amogh Raut +2
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…
GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters
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, con…
Optimizing Tandem Speaker Verification and Anti-Spoofing Systems
Anssi Kanervisto, Ville Hautamäki, Tomi Kinnunen +1
As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve secu…
Improving Behavioural Cloning with Human-Driven Dynamic Dataset Augmentation
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. Such method f…
PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
Yi Ma, Kong Aik Lee, Ville Hautamaki +1
Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion…
VoxCeleb Enrichment for Age and Gender Recognition
Khaled Hechmi, Trung Ngo Trong, Ville Hautamaki +1
VoxCeleb datasets are widely used in speaker recognition studies. Our work serves two purposes. First, we provide speaker age labels and (an alternative) annotation of speaker gend…
Cost Sensitive Optimization of Deepfake Detector
Ivan Kukanov, Janne Karttunen, Hannu Sillanpää +1
Since the invention of cinema, the manipulated videos have existed. But generating manipulated videos that can fool the viewer has been a time-consuming endeavor. With the dramatic…
Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya
Abrhalei Tela, Abraham Woubie, Ville Hautamaki
In recent years, transformer models have achieved great success in natural language processing (NLP) tasks. Most of the current state-of-the-art NLP results are achieved by using m…
Action Space Shaping in Deep Reinforcement Learning
Anssi Kanervisto, Christian Scheller, Ville Hautamäki
Reinforcement learning (RL) has been successful in training agents in various learning environments, including video-games. However, such work modifies and shrinks the action space…
Benchmarking End-to-End Behavioural Cloning on Video Games
Anssi Kanervisto, Joonas Pussinen, Ville Hautamäki
Behavioural cloning, where a computer is taught to perform a task based on demonstrations, has been successfully applied to various video games and robotics tasks, with and without…
Playing Minecraft with Behavioural Cloning
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…
An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning
Anssi Kanervisto, Ville Hautamäki, Tomi Kinnunen +1
The spoofing countermeasure (CM) systems in automatic speaker verification (ASV) are not typically used in isolation of each other. These systems can be combined, for example, into…
Do Autonomous Agents Benefit from Hearing?
Abraham Woubie, Anssi Kanervisto, Janne Karttunen +1
Mapping states to actions in deep reinforcement learning is mainly based on visual information. The commonly used approach for dealing with visual information is to extract pixels…
From Video Game to Real Robot: The Transfer between Action Spaces
Janne Karttunen, Anssi Kanervisto, Ville Kyrki +1
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 challengi…
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
Kong Aik Lee, Ville Hautamaki, Tomi Kinnunen +43
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which…