# Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech

arXiv: https://arxiv.org/abs/2006.08387 · HTML: https://mlsanity.com/paper/2006.08387/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [CTC-based Compression for Direct Speech Translation](https://mlsanity.com/paper/2102.01578/) (2021)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model](https://mlsanity.com/paper/2210.00705/) (2022)
- [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)
- [Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? -- A computational investigation](https://mlsanity.com/paper/2109.14200/) (2021)
- [Modelling word learning and recognition using visually grounded speech](https://mlsanity.com/paper/2203.06937/) (2022)
- [Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks](https://mlsanity.com/paper/2412.15983/) (2024)

## Abstract (arXiv)

The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like units and then break them down into smaller units. This suggests that the ideal way of learning a language is by starting from full semantic units. In this paper, we investigate if this is also the case for a neural model of Visually Grounded Speech trained on a speech-image retrieval task. We evaluated how well such a network is able to learn a reliable speech-to-image mapping when provided with phone, syllable, or word boundary information. We present a simple way to introduce such information into an RNN-based model and investigate which type of boundary is the most efficient. We also explore at which level of the network's architecture such information should be introduced so as to maximise its performances. Finally, we show that using multiple boundary types at once in a hierarchical structure, by which low-level segments are used to recompose high-level segments, is beneficial and yields better results than using low-level or high-level segments in isolation.