mlsanityData to 14 Oct 2026

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

arXiv 2604.01832 ↗First posted 2 Apr 2026eess.AS cs.AI cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

14 of 16 references.

References · 14

  1. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  3. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  4. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 241
  5. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 172
  6. 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 129
  7. 2022TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separationcited by 63
  8. 2024URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancementcited by 17
  9. 2021DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancementcited by 14
  10. 2025Interspeech 2025 URGENT Speech Enhancement Challengecited by 12
  11. 2025PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancementcited by 5
  12. 2026ICASSP 2026 URGENT Speech Enhancement Challengecited by 4
2 more
  1. 2025TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Networkcited by 2
  2. 2025FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challengecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinationscited by 0