文章摘要
宋昊,刘雪洁,俞胜锋,钟小丽.基于深度学习的双耳声源定位算法研究[J].声学技术,2022,41(4):602~607
基于深度学习的双耳声源定位算法研究
Binaural localization algorithm based on deep learning
投稿时间:2021-03-01  修订日期:2021-05-04
DOI:10.16300/j.cnki.1000-3630.2022.04.018
中文关键词: 双耳声源定位  深度学习  卷积神经网络
英文关键词: binaural localization algorithm  deep learning  convolutional neural network (CNN)
基金项目:广东省自然科学基金项目(2021A1515011871,2021A1515012630)
作者单位E-mail
宋昊 广东工业大学管理学院, 广东广州 510000  
刘雪洁 华南师范大学物理与电信工程学院, 广东广州 510006  
俞胜锋 华南理工大学物理与光电学院, 广东广州 510640  
钟小丽 华南理工大学物理与光电学院, 广东广州 510640 xlzhong@scut.edu.cn 
摘要点击次数: 1023
全文下载次数: 1363
中文摘要:
      针对多种定位因素存在复杂关联且不易准确提取的问题,提出了以完整双耳声信号作为输入的、基于深度学习的双耳声源定位算法。首先,分别采用深层全连接后向传播神经网络(Deep Back Propagation Neural Network,D-BPNN)和卷积神经网络(Convolutional Neural Network, CNN)实现深度学习框架;然后,分别以水平面 15°、30°和 45°空间角度间隔的双耳声信号进行模型训练;最后,采用前后混乱率、定位准确率与训练时长等指标进行算法有效性分析。模型预测结果表明,CNN模型的前后混乱率远低于 D-BPNN;D-BPNN模型的定位准确率能够达到87%以上,而 CNN模型的定位准确率能够达到 98%左右;在相同实验条件下,CNN模型的训练时长大于 D-BPNN,且随着水平面角度间隔的减小,两者训练时长之间的差异愈发显著。
英文摘要:
      Due to existence of complicated relationships between multiple localization cues, which causes them hard to be extracted accurately, a deep learning-based binaural sound source localization algorithm with complete binaural sound signals as input is proposed. Firstly, the deep fully connected back propagation neural network (D-BPNN) and the convolutional neural network (CNN) are used to implement the deep learning framework respectively. And then, binaural sound source signals with uniform azimuthal spacing of 15°, 30° and 45° in horizontal plane are applied to model training respectively. Finally, indicators such as front-back confusion rate, localization accuracy and training duration are used to investigate effectiveness of the models. The model prediction results show that the front-back confusion rate of the CNN model is much lower than that of D-BPNN model. The localization accuracy of the DBPNN model can reach more than 87%, while the localization accuracy of the CNN model is about 98%. Under the same experimental conditions, the training time of CNN model is longer than that of D-BPNN model; Moreover, this difference in training time becomes more and more obviously as the azimuthal spacing in the horizontal plane decreases.
查看全文   查看/发表评论  下载PDF阅读器
关闭