# Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction

arXiv: https://arxiv.org/abs/2306.08454 · HTML: https://mlsanity.com/paper/2306.08454/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2023.

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

- [MaskSR: Masked Language Model for Full-band Speech Restoration](https://mlsanity.com/paper/2406.02092/) (2024)
- [Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility](https://mlsanity.com/paper/2409.09357/) (2024)
- [RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention](https://mlsanity.com/paper/2406.07498/) (2024)
- [Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching](https://mlsanity.com/paper/2603.12837/) (2026)

## Abstract (arXiv)

This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is a two-stage architecture, in which the speech restoration is performed, and then cascaded by speech enhancement. We propose a complex spectral mapping-based generative adversarial network (CSM-GAN) as the speech restoration module for the first time. For noise suppression and dereverberation, the enhancement module is performed with fullband-wideband parallel processing. On the blind test set of ICASSP 2023 SSI Challenge, the proposed Gesper system, which satisfies the real-time condition, achieves 3.27 P.804 overall mean opinion score (MOS) and 3.35 P.835 overall MOS, ranked 1st in both track 1 and track 2.