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
Conference NameAnnual Conference of the International Speech Communication Association-Interspeech
Conference DateAugust 20–24, 2017
Conference PlaceStockholm, Sweden
AbstractMany 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.
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15470
Collection模式识别国家重点实验室_语音交互
Affiliation1.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
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
2.pdf(343KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiaoke Qi]'s Articles
[Jianhua Tao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiaoke Qi]'s Articles
[Jianhua Tao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiaoke Qi]'s Articles
[Jianhua Tao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.