RATS

The RATS dataset is used to evaluate the performance of speech processing models in simulating noisy speech from clean speech.

Papers using RATS (3)

Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition2022 · 1 citesStudy of GANs for Noisy Speech Simulation from Clean Speech2023 · 1 citesGradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition2023