摘要
为了更精确地从语谱图中提取特征信息,提出了一种基于A-DResUnet的语音增强方法。A-DResUnet模型在ResUnet模型的基础上融合了空洞卷积,提升捕获语音上下文信息的能力;同时在编码器中加入卷积注意力模块(CBAM),提高对噪声谱图特征的关注。实验结果表明,与模型输出目标为干净语音语谱图相比,用噪声谱图作为模型输出目标时,该模型对未知噪声具有更强的分离能力;相较ResUnet模型,提出的A-DResUnet模型减少了语音细节信息的损失;对比基于DNN、GAN的语音增强方法,PESQ平均提升了22.81%、33.11%,STOI平均提升了9.62%、15.33%,为复杂环境下的语音增强提供了一种更有效的方法。
In order to extract feature information from spectrogram more accurately,this paper proposes a speech enhancement method based on A-DResUnet(attention-dilated ResUnet).The A-DResUnet model incorporates dilated convolution on the basis of ResUnet model to improve the ability to capture the contextual information of speech;at the same time,the convolution block attention module(CBAM)is added into the ResUnet encoder to improve the attention to the features of the noise spectrogram.The experimental results show that when the noise spectrum is used as the output target of the model,the model has a stronger ability to separate unknown noise than when the output target of the model is clean speech spectrum;compared with the ResUnet model,the proposed A-DResUnet model reduces the loss of speech detail information;compared with the speech enhancement methods based on DNN and GAN,PESQ increased by an average of 22.81%,33.11%,STOI increased by an average of 9.62%,15.33%,which is a more effective method for speech enhancement in complex environments.
作者
李吉祥
倪旭昇
颜上取
邹孝
钱盛友
Li Jixiang;Ni Xusheng;Yan Shangqu;Zou Xiao;Qian Shengyou(School of Physics and Electronics,Hunan Normal University,Changsha 410081,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2022年第10期131-137,共7页
Journal of Electronic Measurement and Instrumentation
基金
国家自然科学基金(11774088)项目资助
关键词
语音增强
语谱图
模型输出目标
空洞卷积
卷积注意力模块
speech enhancement
spectrogram
the output target of the model
dilated convolution
convolution block attention module
