AI in EE

AI IN DIVISIONS

AI in Signal Division

AI in EE

AI IN DIVISIONS

AI in Signal Division ​ ​

AI in Signal Division

Hindi as a second language: improving visually grounded speech with semantically similar samples (정준선 교수 연구실)

Title: Hindi as a second language: improving visually grounded speech with semantically similar samples

Authors: H. Ryu, A. Senocak, I. S. Kweon, J. S. Chung

Conference: International Conference on Acoustics, Speech, and Signal Processing

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.

Main Figure: 5