Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese

By William N. Havard, Jean-Pierre Chevrot, Laurent Besacier. 2019

26 citations recorded by the source corpus.

We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese. Experimental results show that attention focuses on nouns and this behaviour holds true for two very typologically different languages. We also draw parallels between artificial neural attention and human attention and show that neural attention focuses on word endings as it has been theorised for human attention. Finally, we investigate how two visually grounded monolingual models can be used to perform cross-lingual speech-to-speech retrieval. For both languages, the enriched bilingual (speech-image) corpora with part-of-speech tags and forced alignments are distributed to the community for reproducible research.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning, Speech & Audio, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Multimodal Learning

In Speech & Audio

In Cognitive Science & Psychology

Citations in the corpus

Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, methodology): “…2019; Ilharco et al., 2019; Eloff et al., 2019a), application to multilingual settings (Harwath et al., 2018a; Kamper & Roth, 2017; Azuh et al., 2019; Havard et al., 2019a), analysis of the linguistic abstractions, such as words and phones, which are learned by the models (Harwath & Glass, 2017;…”
Towards Bilingual Lexicon Discovery From Visually Grounded Speech Audio (2019, unknown): “[5] recently showed that joint image and speech training performs well on cross lingual caption retrieval using English and Hindi, serving as a basis for speech to speech pseudo translation and [26] confirmed this result using an English-Japanese dataset.”
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units (2020, methodology): “…using ∗ Equal contribution visual grounding objectives (Synnaeve et al., 2014; Harwath and Glass, 2015; Harwath et al., 2016; Kamper et al., 2017; Havard et al., 2019a; Merkx et al., 2019; Chrupała et al., 2017; Alishahi et al., 2017; Scharenborg et al., 2018; Hsu and Glass, 2018a; Kamper et…”