Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

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

Résumé

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. Index Terms-grounded language learning, attention mechanism , cross-lingual speech retrieval, recurrent neural networks.
Fichier principal
Vignette du fichier
1902.03052.pdf (543.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02013984 , version 1 (11-02-2019)

Identifiants

Citer

William N Havard, Jean-Pierre Chevrot, Laurent Besacier. Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese. International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, United Kingdom. pp.8618-8622, ⟨10.1109/ICASSP.2019.8683069⟩. ⟨hal-02013984⟩

Relations

160 Consultations
308 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More