aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio

Open paper
Benchmark Model Rank Results
speech-enhancement-on-deep-noise-suppressionaTENNuate–PESQ-WB: 2.98
speech-enhancement-on-demandaTENNuate–PESQ (wb): 3.27CBAK: 2.85COVL: 3.96CSIG: 4.57SI-SDR: 15.04

Rank counts only results with a code link.