Displaying 7 resources

An Open Dataset of Synthetic Speech

This paper introduces a multilingual, multispeaker dataset composed of synthetic and natural speech, designed to foster research and benchmarking in synthetic speech detection.

Category
Semantic knowledge, Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Software resources

Decentralized-gnn

A package for implementing and simulating decentralized Graph Neural Network algorithms for classification of peer-to-peer nodes.

Category
System architectures, Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Software resources

JGNN library for native Java implementation of graph neural networks

Graph Neural Networks (GNNs) have seen a dramatic increase in popularity thanks to their ability to understand relations between graph nodes.

Category
Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Software resources

Word-Class Embeddings for Multiclass Text Classification

Code for Word-Class Embeddings (WCEs), a form of supervised embeddings especially suited for multiclass text classification.

Category
Semantic knowledge, Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Software resources

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting.

Category
Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Software resources

AI4Experiments platform

The AI4Experiments platform is an open space for AI developers. The platform offers visual and intuitive design methods. It facilitates the creation of human-centered AI-solutions, building modular structures and using hybrid AI technologies.

Category
Technology methodologies and landscape
Target audience
Individual Citizens/Members of the Society, Private Sector, Researchers and Academic