Learning to Recognise Words using Visually Grounded Speech
This work addresses word recognition in AI models for researchers in speech and vision, but it is incremental as it applies an existing method to analyze recognition dynamics.
The study tackled the problem of word recognition using a Visually Grounded Speech model trained on image-caption pairs, finding that the model could recognize words from partial input and was negatively affected by word competition effects.
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.