# Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?

arXiv: https://arxiv.org/abs/2408.04029 · HTML: https://mlsanity.com/paper/2408.04029/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 65 references that are in the map.
- First posted on arXiv 7 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://mlsanity.com/paper/1808.04776/) (2018)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models](https://mlsanity.com/paper/2205.11503/) (2022)
- [Quality Controlled Paraphrase Generation](https://mlsanity.com/paper/2203.10940/) (2022)
- [Multidimensional Evaluation for Text Style Transfer Using ChatGPT](https://mlsanity.com/paper/2304.13462/) (2023)
- [Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors](https://mlsanity.com/paper/2107.08337/) (2021)
- [A Data-Driven Investigation of Noise-Adaptive Utterance Generation with Linguistic Modification](https://mlsanity.com/paper/2210.10252/) (2022)

## Abstract (arXiv)

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically difficult environment, is an under-explored topic. We conduct the first study to evaluate LLMs on a novel task of generating acoustically intelligible paraphrases for better human speech perception in noise. Our experiments in English demonstrated that with standard prompting, LLMs struggle to control the non-textual attribute, i.e., acoustic intelligibility, while efficiently capturing the desired textual attributes like semantic equivalence. To remedy this issue, we propose a simple prompting approach, prompt-and-select, which generates paraphrases by decoupling the desired textual and non-textual attributes in the text generation pipeline. Our approach resulted in a 40% relative improvement in human speech perception, by paraphrasing utterances that are highly distorted in a listening condition with babble noise at a signal-to-noise ratio (SNR) -5 dB. This study reveals the limitation of LLMs in capturing non-textual attributes, and our proposed method showcases the potential of using LLMs for better human speech perception in noise.