Learning to Recognise Words Using Visually Grounded Speech
| Autor: | Sebastiaan Scholten, Odette Scharenborg, Danny Merkx |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Visually grounded speech Computer science Speech recognition Recurrent neural network Speech processing Visualization Speech model Flickr8k Word recognition Statistical analysis Computation and Language (cs.CL) Image retrieval Analysis Word (computer architecture) |
| Zdroj: | ISCAS 2021 IEEE International Symposium on Circuits and Systems (ISCAS) |
| DOI: | 10.1109/iscas51556.2021.9401692 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|