arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07330eess.AS
收藏

基于神经网络的实时语音增强的调制域损失

A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement

Tyler Vuong, Yangyang Xia, Richard M. Stern

摘要:

我们描述了基于深度学习的语音增强系统的调制域损失函数。可学习的频谱时间感受野(STRFs)进行了调整,以优化扬声器识别任务。然后,学习的STRF用于计算调制域中的加权均方误差(MSE),用于训练语音增强系统。实验表明,将调制域MSE添加到频谱-时间域中的MSE实质上改善了实时语音增强系统的语音质量和可懂度的客观预测,而不会在推理期间引起额外的计算。

英文摘要:

We describe a modulation-domain loss function for deep-learning-based speech enhancement systems. Learnable spectro-temporal receptive fields (STRFs) were adapted to optimize for a speaker identification task. The learned STRFs were then used to calculate a weighted mean-squared error (MSE) in the modulation domain for training a speech enhancement system. Experiments showed that adding the modulation-domain MSE to the MSE in the spectro-temporal domain substantially improved the objective prediction of speech quality and intelligibility for real-time speech enhancement systems without incurring additional computation during inference.

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。

↑