Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System

碩士 === 中興大學 === 統計學研究所 === 99 === This paper is mainly to discuss the speech recognition of 337 isolation mandarin words for speaker dependent. The feature is Mel-frequency cepstrum coefficient(Mfcc), and the method is k-nearest neighbor(knn), for the recognition, we try to find out the optimal par...

Full description

Bibliographic Details
Main Authors:	Jhong-Da Wu, 吳忠達
Other Authors:	Chung-Bow Lee
Format:	Others
Language:	zh-TW
Published:	2011
Online Access:	http://ndltd.ncl.edu.tw/handle/47366663775116977709

id	ndltd-TW-099NCHU5337008
record_format	oai_dc
spelling	ndltd-TW-099NCHU53370082015-10-13T20:18:50Z http://ndltd.ncl.edu.tw/handle/47366663775116977709 Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System 利用K最近鄰居方法以及最佳梅爾頻率倒頻譜係數之特徵辨識特定語者之中文單音 Jhong-Da Wu 吳忠達碩士中興大學統計學研究所 99 This paper is mainly to discuss the speech recognition of 337 isolation mandarin words for speaker dependent. The feature is Mel-frequency cepstrum coefficient(Mfcc), and the method is k-nearest neighbor(knn), for the recognition, we try to find out the optimal parameters to obtain high performance recognition. Six experimental factors(the length of frame, the dimension of Mfcc, the number of frame, the weight of consonant and vowel, the swing of frame and the duration of consonant) we considered in the work. We find that the best average rate of recognition in database attains 91.5%. Chung-Bow Lee 李宗寶 2011 學位論文 ; thesis 40 zh-TW
collection	NDLTD
language	zh-TW
format	Others
sources	NDLTD
description	碩士 === 中興大學 === 統計學研究所 === 99 === This paper is mainly to discuss the speech recognition of 337 isolation mandarin words for speaker dependent. The feature is Mel-frequency cepstrum coefficient(Mfcc), and the method is k-nearest neighbor(knn), for the recognition, we try to find out the optimal parameters to obtain high performance recognition. Six experimental factors(the length of frame, the dimension of Mfcc, the number of frame, the weight of consonant and vowel, the swing of frame and the duration of consonant) we considered in the work. We find that the best average rate of recognition in database attains 91.5%.
author2	Chung-Bow Lee
author_facet	Chung-Bow Lee Jhong-Da Wu 吳忠達
author	Jhong-Da Wu 吳忠達
spellingShingle	Jhong-Da Wu 吳忠達 Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
author_sort	Jhong-Da Wu
title	Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
title_short	Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
title_full	Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
title_fullStr	Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
title_full_unstemmed	Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System
title_sort	using k-nearest neighbor method and the optimal mel-frequency cepstrum coefficient feature to recognize isolated mandarin word for speaker-dependent system
publishDate	2011
url	http://ndltd.ncl.edu.tw/handle/47366663775116977709
work_keys_str_mv	AT jhongdawu usingknearestneighbormethodandtheoptimalmelfrequencycepstrumcoefficientfeaturetorecognizeisolatedmandarinwordforspeakerdependentsystem AT wúzhōngdá usingknearestneighbormethodandtheoptimalmelfrequencycepstrumcoefficientfeaturetorecognizeisolatedmandarinwordforspeakerdependentsystem AT jhongdawu lìyòngkzuìjìnlínjūfāngfǎyǐjízuìjiāméiěrpínlǜdàopínpǔxìshùzhītèzhēngbiànshítèdìngyǔzhězhīzhōngwéndānyīn AT wúzhōngdá lìyòngkzuìjìnlínjūfāngfǎyǐjízuìjiāméiěrpínlǜdàopínpǔxìshùzhītèzhēngbiànshítèdìngyǔzhězhīzhōngwéndānyīn
_version_	1718045932671467520

Using K-Nearest Neighbor Method and the Optimal Mel-Frequency Cepstrum Coefficient Feature to Recognize Isolated Mandarin Word for Speaker-Dependent System

Similar Items