Learning to Recognise Words using Visually Grounded Speech

TL;DR

This paper explores how a visually grounded speech model can recognize words from spoken captions by embedding isolated words and retrieving images, revealing effects similar to human speech processing.

Contribution

It demonstrates that a visually grounded speech model can recognize words and exhibit human-like word competition effects during recognition.

Findings

Model can recognize words from spoken captions.

Recognition is possible from partial input.

Word competition influences recognition timing.

Abstract

We investigated word recognition in a Visually Grounded Speech model. The model has been trained on pairs of images and spoken captions to create visually grounded embeddings which can be used for speech to image retrieval and vice versa. We investigate whether such a model can be used to recognise words by embedding isolated words and using them to retrieve images of their visual referents. We investigate the time-course of word recognition using a gating paradigm and perform a statistical analysis to see whether well known word competition effects in human speech processing influence word recognition. Our experiments show that the model is able to recognise words, and the gating paradigm reveals that words can be recognised from partial input as well and that recognition is negatively influenced by word competition from the word initial cohort.