This paper demonstrates three different systems capable of performing the multimodal word discovery task. A multimodal word discovery system accepts, as input, a database of spoken descriptions of images (or a set of corresponding phone transcripts), and learns a lexicon which is a mapping from phone strings to their associated image concepts. Three systems are demonstrated: one based on a statistical machine translation (SMT) model, two based on neural machine translation (NMT). On Flickr8k, the SMT-based model performs much better than the NMT-based one, achieving a 49.6% F1 score. Finally, we apply our word discovery system to the task of image retrieval and achieve 29.1% recall@10 on the standard 1000-image Flickr8k tests set.
Cite as: Wang, L., Hasegawa-Johnson, M.A. (2019) Multimodal Word Discovery and Retrieval with Phone Sequence and Image Concepts. Proc. Interspeech 2019, 2683-2687, doi: 10.21437/Interspeech.2019-1487
@inproceedings{wang19g_interspeech,
author={Liming Wang and Mark A. Hasegawa-Johnson},
title={{Multimodal Word Discovery and Retrieval with Phone Sequence and Image Concepts}},
year=2019,
booktitle={Proc. Interspeech 2019},
pages={2683--2687},
doi={10.21437/Interspeech.2019-1487}
}