Hindi As A Second Language: Improving Visually Grounded Speech With Semantically Similar Samples

Abstract

The objective of this work is to explore the learning of visually grounded speech models (VGS) from multilingual perspective. Bilingual VGS models are generally trained with an equal number of spoken captions from both languages. However, in reality, there can be an imbalance among the languages for the available spoken captions. Our key contribution in this work is to leverage the power of a high-resource language in a bilingual visually grounded speech model to improve the performance of a low-resource language. We introduce two methods to distill the knowledge of high-resource language into low-resource languages: (1) incorporating a strong pre-trained high-resource language encoder and (2) using semantically similar spoken captions. Our experiments show that combining these two approaches effectively enables the low-resource language to surpass the performances of monolingual and bilingual counterparts for cross-modal retrieval tasks.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyryu2023hindi

Related papers

• Visually Grounded Speech Models For Low-resource Languages And Cognitive Modelling (2024)0.00
• Vision As An Interlingua: Learning Multilingual Semantic Embeddings Of Untranscribed Speech (2018)10.74
• Visually Grounded Keyword Detection And Localisation For Low-resource Languages (2023)0.00
• Evaluation Of Audio-visual Alignments In Visually Grounded Speech Models (2021)5.84
• On The Contributions Of Visual And Textual Supervision In Low-resource Semantic Speech Retrieval (2019)6.34
• Semantic Speech Retrieval With A Visually Grounded Model Of Untranscribed Speech (2017)10.61
• Leveraging Pretrained Image-text Models For Improving Audio-visual Learning (2023)0.00
• Large-scale Representation Learning From Visually Grounded Untranscribed Speech (2019)10.48