Summary of What Do Language Models Hear? Probing For Auditory Representations in Language Models, by Jerry Ngo et al.
What Do Language Models Hear? Probing for Auditory Representations in Language Models
by Jerry Ngo, Yoon Kim
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper investigates whether language models can learn meaningful representations of object sounds. A linear probe is designed to retrieve the correct text representation of an object given a snippet of audio related to that object, using a pre-trained audio model as the sound representation. The probe is trained using a contrastive loss function that encourages the language and sound representations of an object to be similar. After training, the probe is tested on its ability to generalize to unseen objects, showing promising results across different language and audio models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how well language models can learn about what things sound like. They create a special tool that takes in some sounds related to an object and tries to find the right words to describe it. The tool is trained by looking at lots of objects and their corresponding sounds, and then it’s tested on new objects it hasn’t seen before. The results show that language models can pick up on what things sound like for certain objects. |
Keywords
* Artificial intelligence * Contrastive loss
