An Adaptation Method in Noise Mismatch Conditions for DNN-based Speech Enhancement

• Xu Si-Ying,
• Niu Tong,
• Qu Dan,
• Long Xing-Yan,

Vol. 12, No. 10, October 30, 2018
10.3837/tiis.2018.10.017, Download Paper (Free):

• Noise-aware Training
• identity-vector, L2 regularization, speech enhancement, DNN, condition mismatch

Abstract

The deep learning based speech enhancement has shown considerable success. However, it still suffers performance degradation under mismatch conditions. In this paper, an adaptation method is proposed to improve the performance under noise mismatch conditions. Firstly, we advise a noise aware training by supplying identity vectors (i-vectors) as parallel input features to adapt deep neural network (DNN) acoustic models with the target noise. Secondly, given a small amount of adaptation data, the noise-dependent DNN is obtained by using L2 regularization from a noise-independent DNN, and forcing the estimated masks to be close to the unadapted condition. Finally, experiments were carried out on different noise and SNR conditions, and the proposed method has achieved significantly 0.1%-9.6% benefits of STOI, and provided consistent improvement in PESQ and segSNR against the baseline systems.

Statistics

Cite this article