arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.02253eess.AScs.CLcs.SD
收藏

周期一致的语音增强

Cycle-Consistent Speech Enhancement

Microsoft AI and Research(微软人工智能与研究部)

Zhong Meng, Jinyu Li, Yifan Gong, Biing-Hwang, Juang

摘要:

使用深度神经网络的特征映射是单通道语音增强的有效方法。通过映射网络将噪声特征转换为增强特征,并使增强特征与干净特征之间的均方误差最小化。在本文中,我们提出了一个循环一致的语音增强(CSE),其中一个额外的逆映射网络被引入到重建的噪声功能,从增强的。一个周期一致的约束,以尽量减少重建损失。类似地,在具有相同网络和损耗的相反方向上执行映射的反向循环。通过循环一致性,语音结构在增强的特征中得到很好的保留,同时有效地减少了噪声,使得特征映射网络更好地推广到看不见的数据。在只有无与伦比的噪声和干净的数据可用于训练的情况下,使用两个神经网络来区分增强的和噪声的特征与干净的和噪声的特征。通过对抗性多任务学习,识别损失与重建损失联合优化。在CHiME-3数据集上进行的测试表明,该算法在使用和不使用并行的干净语音和噪声语音数据时,相对误词率分别提高了19.60%和6.69%。

英文摘要:

Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and clean features are minimized. In this paper, we propose a cycle-consistent speech enhancement (CSE) in which an additional inverse mapping network is introduced to reconstruct the noisy features from the enhanced ones. A cycle-consistent constraint is enforced to minimize the reconstruction loss. Similarly, a backward cycle of mappings is performed in the opposite direction with the same networks and losses. With cycle-consistency, the speech structure is well preserved in the enhanced features while noise is effectively reduced such that the feature-mapping network generalizes better to unseen data. In cases where only unparalleled noisy and clean data is available for training, two discriminator networks are used to distinguish the enhanced and noised features from the clean and noisy ones. The discrimination losses are jointly optimized with reconstruction losses through adversarial multi-task learning. Evaluated on the CHiME-3 dataset, the proposed CSE achieves 19.60% and 6.69% relative word error rate improvements respectively when using or without using parallel clean and noisy speech data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑