Investigation of High Confused Mandarin Vowel Recognition on DNN ,CNN and CapsNet
碩士 === 國立中興大學 === 統計學研究所 === 107 === This paper is to explore the differences in recognition between DNN(Deep Neural Networks), CNN(Convolutional Neural Networks), and CapsNet(Capsule Networks) on the 15 kinds of high confused Mandarin vowels recognition such as< ㄢ、ㄤ >, < ㄛ、ㄨㄛ >, < ㄥ、ㄣ >, a...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5337001%22.&searchmode=basic |