Summary of Audiobert: Audio Knowledge Augmented Language Model, by Hyunjong Ok et al.
AudioBERT: Audio Knowledge Augmented Language Model
by Hyunjong Ok, Suho Yoo, Jaeho Lee
First submitted to arxiv on: 12 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 Recent studies have shown that language models, pretrained on text-only datasets, often lack basic visual knowledge. Similarly, this study investigates whether a similar shortcoming exists in auditory knowledge. To answer this question, the authors construct a new dataset called AuditoryBench, which consists of two novel tasks for evaluating auditory knowledge. The analysis reveals that language models also suffer from a severe lack of auditory knowledge. To address this limitation, the authors propose AudioBERT, a novel method to augment the auditory knowledge of BERT through a retrieval-based approach. AudioBERT detects auditory knowledge spans in prompts and injects audio knowledge into BERT, switching on low-rank adaptation for effective adaptation when audio knowledge is required. Experimental results demonstrate that AudioBERT achieves superior performance on the AuditoryBench dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at whether language models have a problem with understanding sounds. Right now, they’re only good at understanding text. The researchers created a new dataset to test their auditory knowledge and found that language models are not very good at it either. To fix this problem, the authors came up with a new way of training language models called AudioBERT. It helps language models understand audio by detecting what kind of sounds are in prompts and adding that information to the model. The results show that AudioBERT works really well. |
Keywords
» Artificial intelligence » Bert » Low rank adaptation
