Classification of partial discharge images using deep convolutional neural networks

M Florkowski - Energies, 2020 - mdpi.com
Artificial intelligence-based solutions and applications have great potential in various fields
of electrical power engineering. The problem of the electrical reliability of power equipment …

Optimizing tandem speaker verification and anti-spoofing systems

A Kanervisto, V Hautamäki, T Kinnunen… - … on Audio, Speech …, 2021 - ieeexplore.ieee.org
As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are
typically used in conjunction with spoofing countermeasure (CM) systems to improve …

Automatic Assessment of Parkinson's Disease Using Speech Representations of Phonation and Articulation

Y Liu, MK Reddy, N Penttilä, T Ihalainen… - … on Audio, Speech …, 2022 - ieeexplore.ieee.org
Speech from people with Parkinson's disease (PD) are likely to be degraded on phonation,
articulation, and prosody. Motivated to describe articulation deficits comprehensively, we …

Cost sensitive optimization of deepfake detector

I Kukanov, J Karttunen, H Sillanpää… - 2020 Asia-Pacific …, 2020 - ieeexplore.ieee.org
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 …

[PDF][PDF] Recurrent neural network and maximal figure of merit for acoustic event detection

I Kukanov, V Hautamäki, KA Lee - Proceedings of the Workshop …, 2017 - dcase.community
In this report, we describe the systems submitted to the DCASE 2017 challenge. In
particular, we explored convolutional recurrent neural network (CRNN) for acoustic scene …

Maximal figure-of-merit framework to detect multi-label phonetic features for spoken language recognition

I Kukanov, TN Trong, V Hautamäki… - … on Audio, Speech …, 2020 - ieeexplore.ieee.org
Bottleneck features (BNFs) generated with a deep neural network (DNN) have proven to
boost spoken language recognition accuracy over basic spectral features significantly …

Maximal figure-of-merit embedding for multi-label audio classification

I Kukanov, V Hautamäki, KA Lee - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
This work tackles the problem of the domestic audio tagging or environmental sound
classification, where one audio recording can contain one or more acoustic events and a …

An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning

A Kanervisto, V Hautamäki, T Kinnunen… - arXiv preprint arXiv …, 2020 - arxiv.org
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 a …

Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks

D Wang, X Zhang - Sensors, 2019 - mdpi.com
Field monitoring serves as an important supervision tool in a variety of engineering domains.
An efficient monitoring would trigger an alarm timely once it detects an out-of-control event …

[PDF][PDF] PLATFORMĂ DE MENTENANȚĂ ÎN INDUSTRIA 4.0

GDC Narcisa, CE COTEȚ - docs.upb.ro
Ca urmare a noii revoluții industriale (Industry 4.0), ne regăsim într-o perioadă caracterizată
de automatizarea, digitizarea și interconectarea componentelor din procesele de producție …