Displaying 15 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

ToDY: Time of Day/Year: Dataset for visual time of day and season classification

The dataset provides training and valiation data for classifying images by time of day and season (time of year). The images are taken from the Skyfinder dataset, containing webcam images along with timestamps and geolocation.

Category
Data sharing and Data spaces
Target audience
ADR Experts and Associations, Researchers and Academic