# iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning

arXiv: https://arxiv.org/abs/2004.00932 · HTML: https://mlsanity.com/paper/2004.00932/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech](https://mlsanity.com/paper/2110.05866/) (2021)
- [SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks](https://mlsanity.com/paper/2210.14474/) (2022)
- [A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech](https://mlsanity.com/paper/2210.15368/) (2022)

## Abstract (arXiv)

The intelligibility of natural speech is seriously degraded when exposed to adverse noisy environments. In this work, we propose a deep learning-based speech modification method to compensate for the intelligibility loss, with the constraint that the root mean square (RMS) level and duration of the speech signal are maintained before and after modifications. Specifically, we utilize an iMetricGAN approach to optimize the speech intelligibility metrics with generative adversarial networks (GANs). Experimental results show that the proposed iMetricGAN outperforms conventional state-of-the-art algorithms in terms of objective measures, i.e., speech intelligibility in bits (SIIB) and extended short-time objective intelligibility (ESTOI), under a Cafeteria noise condition. In addition, formal listening tests reveal significant intelligibility gains when both noise and reverberation exist.