|
作者 | Minghao Yang1,2 ; Dawei Zhang1 ; Jianhua Tao1,2,3
|
出版日期 | 2018
|
会议日期 | 2018.08.20-2018.08.24
|
会议地点 | 北京
|
关键词 | Vocal Tract
Neural Network
Tongue Shape
Pca
|
英文摘要 | In spite of various observation tools, tongue shapes
are still scarce resource in reality. Autoencoder, a kind of deep
neural networks (DNN), performs well on data reduction and
pattern discovery. However, since autoencoder usually needs
large scale data in training, challenges exist for traditional
autoencoder to obtain tongues' motion patterns only from tens or
hundreds of available tongue shapes. To overcome this problem,
we propose a two-steps autoencoder, where we first construct a
stacked denoising autoencoder (dAE) to learn the essential
presentation of the tongue shapes from their possible
deformations; then an additional autoencoder with small number
of hidden units is added upon the previous stacked autoencoder,
and used for dimensionality reduction. Experiments run on 240
vowels' tongue shapes obtained from Chinese speakers'
pronunciation X-ray films, and the proposed model is compared
with traditional dAE and the classical principal component
analysis (PCA) on dimensionality reduction and reconstruction in
details. Results validate the performance of the proposed tongue
model. |
语种 | 英语
|
源URL | [http://ir.ia.ac.cn/handle/173211/26176]  |
专题 | 模式识别国家重点实验室_智能交互
|
作者单位 | 1.National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences 2.The Center for Excellence in Brain Science and Intelligent Technology of Chinese Academy of Sciences 3.University of Chinese Academy of Sciences
|
推荐引用方式 GB/T 7714 |
Minghao Yang,Dawei Zhang,Jianhua Tao. Reducing Tongue Shape Dimensionality from Hundreds of Available Resources Using Autoencoder[C]. 见:. 北京. 2018.08.20-2018.08.24.
|