MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
(3 minutes introduction)
| Szu-Wei Fu (Academia Sinica, Taiwan), Cheng Yu (Academia Sinica, Taiwan), Tsun-An Hsieh (Academia Sinica, Taiwan), Peter Plantinga (Ohio State University, USA), Mirco Ravanelli (Mila, Canada), Xugang Lu (NICT, Japan), Yu Tsao (Academia Sinica, Taiwan) |
|---|
The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three training techniques incorporating domain-knowledge of speech processing are proposed. With these techniques, experimental results on the VoiceBank-DEMAND dataset show that MetricGAN+ can increase PESQ score by 0.3 compared to the previous MetricGAN and achieve state-of-the-art results (PESQ score = 3.15).
