End-to-End Multi-Task Denoising for joint SDR and PESQ Optimization

Understand

Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement.

• Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio between clean and noisy spectra.
• In either case, the network is optimized by minimizing mean square error (MSE) between ground-truth labels and time-domain or spectrum output.
• However, existing schemes have either of two critical issues: spectrum and metric mismatches.