Open Challenges in Synthetic Speech Detection

no code implementations • 15 Sep 2022 • Luca Cuccovillo, Christoforos Papastergiopoulos, Anastasios Vafeiadis, Artem Yaroshchuk, Patrick Aichroth, Konstantinos Votis, Dimitrios Tzovaras

In this paper the current status and open challenges of synthetic speech detection are addressed.

Synthetic Speech Detection

Image-based Natural Language Understanding Using 2D Convolutional Neural Networks

no code implementations • 24 Oct 2018 • Erinc Merdivan, Anastasios Vafeiadis, Dimitrios Kalatzis, Sten Hanke, Johannes Kropf, Konstantinos Votis, Dimitrios Giakoumis, Dimitrios Tzovaras, Liming Chen, Raouf Hamzaoui, Matthieu Geist

We propose a new approach to natural language understanding in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations ofthe visual patterns of words.

General Classification Natural Language Understanding +4

Towards Unsupervised Classification with Deep Generative Models

no code implementations • ICLR 2018 • Dimitris Kalatzis, Konstantia Kotta, Ilias Kalamaras, Anastasios Vafeiadis, Andrew Rawstron, Dimitris Tzovaras, Kostas Stamatopoulos

Deep generative models have advanced the state-of-the-art in semi-supervised classification, however their capacity for deriving useful discriminative features in a completely unsupervised fashion for classification in difficult real-world data sets, where adequate manifold separation is required has not been adequately explored.

Classification Clustering +1