CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
A Domain Knowledge-Assisted Nonlinear Model for Head-Related Transfer Functions Based on Bottleneck Deep Neural Network
Xiaoke Qi1; Jianhua Tao1,2,3
2017
会议名称Annual Conference of the International Speech Communication Association-Interspeech
会议日期August 20–24, 2017
会议地点Stockholm, Sweden
摘要Many methods have been proposed for modeling head-related transfer functions (HRTFs) and yield a good performance level in terms of log-spectral distortion (LSD). However, most of them utilize linear weighting to reconstruct or interpolate HRTFs, but not consider the inherent nonlinearity relationship between the basis function and HRTFs. Motivated by this, a domain knowledge-assisted nonlinear modeling method is proposed based on bottleneck features. Domain knowledge is used in two aspects. One is to generate the input features derived from the solution to sound wave propagation equation at the physical level, and the other is to design the loss function for model training based on the knowledge of objective evaluation criterion, i.e., LSD. Furthermore, with utilizing the strong representation ability of the bottleneck features, the nonlinear model has the potential to achieve a more accurate mapping. The objective and subjective experimental results show that the proposed method gains less LSD when compared with linear model, and the interpolated HRTFs can generate a similar perception to those of the database.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/15470
专题模式识别国家重点实验室_语音交互
作者单位1.National Laboratory of Pattern Recognition (NLPR)
2.CAS Center for Excellence in Brain Science and Intelligence Technology
3.School of Computer and Control Engineering, University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Xiaoke Qi,Jianhua Tao. A Domain Knowledge-Assisted Nonlinear Model for Head-Related Transfer Functions Based on Bottleneck Deep Neural Network[C],2017.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2.pdf(343KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xiaoke Qi]的文章
[Jianhua Tao]的文章
百度学术
百度学术中相似的文章
[Xiaoke Qi]的文章
[Jianhua Tao]的文章
必应学术
必应学术中相似的文章
[Xiaoke Qi]的文章
[Jianhua Tao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。