GAP-URGENet: A Generative-Predictive Fusion Framework for Universal Speech Enhancement

TL;DR

GAP-URGENet is a novel speech enhancement framework combining generative and predictive models to improve robustness and quality, achieving top results in the ICASSP 2026 URGENT Challenge.

Contribution

It introduces a fusion of generative and predictive approaches for speech restoration, with a self-supervised domain and waveform reconstruction, advancing the state-of-the-art in speech enhancement.

Findings

Achieved top performance in the URGENT Challenge blind-test phase.

Fusion of generative and predictive branches enhances robustness and perceptual quality.

Provided high-quality speech enhancement with bandwidth extension to 48 kHz.

Abstract

We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge. The system integrates a generative branch, which performs full-stack speech restoration in a self-supervised representation domain and reconstructs the waveform via a neural vocoder, along with a predictive branch that performs spectrogram-domain enhancement, providing complementary cues. Outputs from both branches are fused by a post-processing module, which also performs bandwidth extension to generate the enhanced waveform at 48 kHz, later downsampled to the original sampling rate. This generative-predictive fusion improves robustness and perceptual quality, achieving top performance in the blind-test phase and ranking 1st in the objective evaluation. Audio examples are available at https://xiaobin-rong.github.io/gap-urgenet_demo.