# Symbolic inductive bias for visually grounded learning of spoken language

arXiv: https://arxiv.org/abs/1812.09244 · HTML: https://mlsanity.com/paper/1812.09244/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2018.

## Built on by (most cited first, 10 of 10)

- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques](https://mlsanity.com/paper/2104.13225/) (2021)
- [Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling](https://mlsanity.com/paper/2202.03543/) (2022)
- [Fast-Slow Transformer for Visually Grounding Speech](https://mlsanity.com/paper/2109.08186/) (2021)
- [Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval](https://mlsanity.com/paper/2104.01894/) (2021)
- [Equivariance and Invariance Inductive Bias for Learning from Insufficient Data](https://mlsanity.com/paper/2207.12258/) (2022)
- [ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition](https://mlsanity.com/paper/2107.06546/) (2021)
- [Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples](https://mlsanity.com/paper/2303.17517/) (2023)
- [Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech](https://mlsanity.com/paper/2112.13758/) (2021)
- [Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models](https://mlsanity.com/paper/2308.08774/) (2023)

## Abstract (arXiv)

A widespread approach to processing spoken language is to first automatically transcribe it into text. An alternative is to use an end-to-end approach: recent works have proposed to learn semantic embeddings of spoken language from images with spoken captions, without an intermediate transcription step. We propose to use multitask learning to exploit existing transcribed speech within the end-to-end setting. We describe a three-task architecture which combines the objectives of matching spoken captions with corresponding images, speech with text, and text with images. We show that the addition of the speech/text task leads to substantial performance improvements on image retrieval when compared to training the speech/image task in isolation. We conjecture that this is due to a strong inductive bias transcribed speech provides to the model, and offer supporting evidence for this.