Search Results for author: Mirjam Ernestus

Found 5 papers, 4 papers with code

Modelling word learning and recognition using visually grounded speech

1 code implementation14 Mar 2022 Danny Merkx, Sebastiaan Scholten, Stefan L. Frank, Mirjam Ernestus, Odette Scharenborg

We furthermore investigate whether vector quantisation, a technique for discrete representation learning, aids the model in the discovery and recognition of words.

Representation Learning speech-recognition +1

Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge

1 code implementation CMCL (ACL) 2022 Danny Merkx, Stefan L. Frank, Mirjam Ernestus

In this paper we create visually grounded word embeddings by combining English text and images and compare them to popular text-based methods, to see if visual information allows our model to better capture cognitive aspects of word meaning.

Grounded language learning Image Retrieval +4

Semantic sentence similarity: size does not always matter

1 code implementation16 Jun 2021 Danny Merkx, Stefan L. Frank, Mirjam Ernestus

This study addresses the question whether visually grounded speech recognition (VGS) models learn to capture sentence semantics without access to any prior linguistic knowledge.

Grounded language learning Image Retrieval +9

The Nijmegen Corpus of Casual Czech

no code implementations LREC 2014 Mirjam Ernestus, Lucie Ko{\v{c}}kov{\'a}-Amortov{\'a}, Petr Pollak

All speakers were native speakers of Czech, raised in Prague or in the region of Central Bohemia, and were between 19 and 26 years old.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

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