# A Data-Driven Investigation of Noise-Adaptive Utterance Generation with Linguistic Modification

arXiv: https://arxiv.org/abs/2210.10252 · HTML: https://mlsanity.com/paper/2210.10252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 47 references that are in the map.
- First posted on arXiv 19 Oct 2022.

## Builds on (most cited first, 6 of 6)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [An evaluation of intrusive instrumental intelligibility metrics](https://mlsanity.com/paper/1708.06027/) (2017)
- [Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors](https://mlsanity.com/paper/2107.08337/) (2021)

## Built on by (most cited first, 1 of 1)

- [Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?](https://mlsanity.com/paper/2408.04029/) (2024)

## Abstract (arXiv)

In noisy environments, speech can be hard to understand for humans. Spoken dialog systems can help to enhance the intelligibility of their output, either by modifying the speech synthesis (e.g., imitate Lombard speech) or by optimizing the language generation. We here focus on the second type of approach, by which an intended message is realized with words that are more intelligible in a specific noisy environment. By conducting a speech perception experiment, we created a dataset of 900 paraphrases in babble noise, perceived by native English speakers with normal hearing. We find that careful selection of paraphrases can improve intelligibility by 33% at SNR -5 dB. Our analysis of the data shows that the intelligibility differences between paraphrases are mainly driven by noise-robust acoustic cues. Furthermore, we propose an intelligibility-aware paraphrase ranking model, which outperforms baseline models with a relative improvement of 31.37% at SNR -5 dB.