Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition
碩士 === 國立中興大學 === 統計學研究所 === 107 === In the past 10 years, with the rise of the artificial neural network, machine learning has made rapid advance in speech and image recognition, while Chinese pronunciation can be divided into two parts: vowel and consonant. Take <ㄈㄚˇ>for example,<ㄈ>is conson...
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=%22107NCHU5337011%22.&searchmode=basic |
id |
ndltd-TW-107NCHU5337011 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107NCHU53370112019-11-30T06:09:39Z http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5337011%22.&searchmode=basic Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition 最近鄰居法與卷積神經網路池化對中文母音辨識之探討 You-Cheng Lin 林祐丞 碩士 國立中興大學 統計學研究所 107 In the past 10 years, with the rise of the artificial neural network, machine learning has made rapid advance in speech and image recognition, while Chinese pronunciation can be divided into two parts: vowel and consonant. Take <ㄈㄚˇ>for example,<ㄈ>is consonant and <ㄚˇ> is vowel . There are 160 types of vowels, 36 types of consonants, and 5 tones which compose 1,391 Chinese pronunciation. In this paper, the k-nearest neighbor(KNN) method and the convolutional neural network(CNN) are used to identify the vowel. The data is recorded from 20 speakers. After sampling, endpoint detection, and frame cutting, the dimension of parameter matrix of each pronunciation data is 53x39, and then attempts to use k-nearest neighbor method , and the convolutional neural network model to identify different hyperparameters with non-pooling, maximum pooling, and average pooling respectively, and explores the effects of various combinations on the accuracy of identification. Because CNN is nonlinear fitting, the recognition rate is much higher than KNN which is linear. The hyperparameter of CNN's highest resolution is 45 frame, kernel size is 5x5, and number of kernel is (512. , 1024, 2048), and using the average pooling, the recognition rate of the vowel can reach 0.9647. 李宗寶 2019 學位論文 ; thesis 21 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中興大學 === 統計學研究所 === 107 === In the past 10 years, with the rise of the artificial neural network, machine learning has made rapid advance in speech and image recognition, while Chinese pronunciation can be divided into two parts: vowel and consonant. Take <ㄈㄚˇ>for example,<ㄈ>is consonant and <ㄚˇ> is vowel . There are 160 types of vowels, 36 types of consonants, and 5 tones which compose 1,391 Chinese pronunciation. In this paper, the k-nearest neighbor(KNN) method and the convolutional neural network(CNN) are used to identify the vowel. The data is recorded from 20 speakers. After sampling, endpoint detection, and frame cutting, the dimension of parameter matrix of each pronunciation data is 53x39, and then attempts to use k-nearest neighbor method , and the convolutional neural network model to identify different hyperparameters with non-pooling, maximum pooling, and average pooling respectively, and explores the effects of various combinations on the accuracy of identification. Because CNN is nonlinear fitting, the recognition rate is much higher than KNN which is linear. The hyperparameter of CNN's highest resolution is 45 frame, kernel size is 5x5, and number of kernel is (512. , 1024, 2048), and using the average pooling, the recognition rate of the vowel can reach 0.9647.
|
author2 |
李宗寶 |
author_facet |
李宗寶 You-Cheng Lin 林祐丞 |
author |
You-Cheng Lin 林祐丞 |
spellingShingle |
You-Cheng Lin 林祐丞 Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
author_sort |
You-Cheng Lin |
title |
Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
title_short |
Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
title_full |
Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
title_fullStr |
Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
title_full_unstemmed |
Applying K-Nearest Neighbor and Convolutional Neural Network pooling on Mandarin Vowel Recognition |
title_sort |
applying k-nearest neighbor and convolutional neural network pooling on mandarin vowel recognition |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5337011%22.&searchmode=basic |
work_keys_str_mv |
AT youchenglin applyingknearestneighborandconvolutionalneuralnetworkpoolingonmandarinvowelrecognition AT línyòuchéng applyingknearestneighborandconvolutionalneuralnetworkpoolingonmandarinvowelrecognition AT youchenglin zuìjìnlínjūfǎyǔjuǎnjīshénjīngwǎnglùchíhuàduìzhōngwénmǔyīnbiànshízhītàntǎo AT línyòuchéng zuìjìnlínjūfǎyǔjuǎnjīshénjīngwǎnglùchíhuàduìzhōngwénmǔyīnbiànshízhītàntǎo |
_version_ |
1719300442630914048 |