#open source
6 resultsThe VIA Annotation Software for Images, Audio and Video
Abhishek Dutta, Andrew Zisserman
The paper presents VIA, a lightweight, browser‑based annotation tool for images, audio, and video that requires no installation and supports defining spatial regions and temporal s…
Do as I Do, Not as I Say: Do Contribution Guidelines Match the GitHub Contribution Process?
Omar Elazhary, Margaret-Anne Storey, Neil Ernst +1
The paper investigates whether the contribution guidelines posted by GitHub projects match the actual contribution workflow, analyzing 53 projects and finding that about two‑thirds…
CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages
Kyubyong Park, Thomas Mulc
The paper presents CSS10, a publicly released collection of single‑speaker speech recordings and aligned texts for ten languages sourced from LibriVox, and validates the data by tr…
DELTA: A DEep learning based Language Technology plAtform
Kun Han, Junwen Chen, Hui Zhang +20
DELTA is an open‑source, deep‑learning platform that integrates popular neural network models and deployment tools to support a range of natural language and speech processing task…
Nefnir: A high accuracy lemmatizer for Icelandic
SvanhvÃt Lilja Ingólfsdóttir, Hrafn Loftsson, Jón Friðrik Daðason +1
The paper presents Nefnir, an open‑source lemmatizer for Icelandic that uses suffix substitution rules derived from a large morphological database, achieving up to 99.55% accuracy…
Git Blame Who?: Stylistic Authorship Attribution of Small, Incomplete Source Code Fragments
Edwin Dauber, Aylin Caliskan, Richard Harang +4
The paper presents a method for attributing authorship of short, incomplete source code fragments by aggregating classification probabilities across multiple samples, achieving nea…