DNS-3

The DNS3 dataset is used to evaluate speech enhancement methods and contains a collection of noisy speech recordings designed to benchmark the performance of various algorithms in improving speech quality.

Papers using DNS-3 (3)

I-DCCRN-VAE: An Improved Deep Representation Learning Framework for Complex VAE-based Single-channel Speech Enhancement2025Investigation of Speech and Noise Latent Representations in Single-channel VAE-based Speech Enhancement2025HALO: Half-Frame-Rate Adaptive Learnable Operator for Lightweight STFT-Based Speech Enhancement2026