Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing
Published in APSIPA ASC, 2020
Recommended citation: S.-W. Fu, C.-F. Liao, T.-A. Hsieh, K.-H. Hung, S.-S. Wang, C. Yu, H.-C. Kuo, R. E Zezario, Y.-J. Li, S.-Y. Chuang, Y.-J. Lu, Y.-C. Lin, Y. Tsao, "Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing,” in Proc. APSIPA ASC, 2020. https://arxiv.org/pdf/2006.10296.pdf
The Transformer architecture has demonstrated a superior ability compared to recurrent neural networks in many different natural language processing applications. Therefore, our study applies a modified Transformer in a speech enhancement task. Specifically, positional encoding in the Transformer may not be necessary for speech enhancement, and hence, it is replaced by convolutional layers. To further improve the perceptual evaluation of the speech quality (PESQ) scores of enhanced speech, the 𝐿1 pre-trained Transformer is fine-tuned using a MetricGAN framework. The proposed MetricGAN can be treated as a general postprocessing module to further boost the objective scores of interest. The experiments were conducted using the data sets provided by the organizer of the Deep Noise Suppression (DNS) challenge. Experimental results demonstrated that the proposed system outperformed the challenge baseline, in both subjective and objective evaluations, with a large margin.
Recommended citation: S.-W. Fu, C.-F. Liao, T.-A. Hsieh, K.-H. Hung, S.-S. Wang, C. Yu, H.-C. Kuo, R. E Zezario, Y.-J. Li, S.-Y. Chuang, Y.-J. Lu, Y.-C. Lin, Y. Tsao, “Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing,” in Proc. APSIPA ASC, 2020.