Search Results for author: David Erik Mollberg

Found 4 papers, 1 papers with code

Samrómur Children: An Icelandic Speech Corpus

no code implementations • LREC 2022 • Carlos Daniel Hernandez Mena, David Erik Mollberg, Michal Borský, Jón Guðnason

Samrómur Children is an Icelandic speech corpus intended for the field of automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Paper
Add Code

Samrómur: Crowd-sourcing large amounts of data

no code implementations • LREC 2022 • Staffan Hedström, David Erik Mollberg, Ragnheiður Þórhallsdóttir, Jón Guðnason

This contribution describes the collection of a large and diverse corpus for speech recognition and similar tools using crowd-sourced donations.

speech-recognition Speech Recognition

Paper
Add Code

Samr\'omur: Crowd-sourcing Data Collection for Icelandic Speech Recognition

no code implementations • LREC 2020 • David Erik Mollberg, {\'O}lafur Helgi J{\'o}nsson, Sunneva {\TH}orsteinsd{\'o}ttir, Stein{\th}{\'o}r Steingr{\'\i}msson, Eyd{\'\i}s Huld Magn{\'u}sd{\'o}ttir, Jon Gudnason

Upon completion, Samr{\'o}mur will be the largest open speech corpus for Icelandic collected from the public domain.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Paper
Add Code

Kvistur 2.0: a BiLSTM Compound Splitter for Icelandic

1 code implementation • LREC 2020 • Jón Friðrik Daðason, David Erik Mollberg, Hrafn Loftsson, Kristín Bjarnadóttir

In this paper, we present a character-based BiLSTM model for splitting Icelandic compound words, and show how varying amounts of training data affects the performance of the model.

Part-Of-Speech Tagging

7

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.