Speech and Breath-Sound-Based Person Identification with Sparse Training Data
碩士 === 國立臺北科技大學 === 電資國際專班 === 107 === This study aims to develop a person identification (PID) system based on combined use of bronchial breath sounds and speech signals acquired by stethoscope. Two major methods, including support vector machines, and artificial neural networks are evaluated in th...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/tpzt27 |
id |
ndltd-TW-107TIT0070A002 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107TIT0070A0022019-05-16T01:31:54Z http://ndltd.ncl.edu.tw/handle/tpzt27 Speech and Breath-Sound-Based Person Identification with Sparse Training Data 以少量語音及呼吸音進行身份識別 TRAN VAN THUAN TRAN VAN THUAN 碩士 國立臺北科技大學 電資國際專班 107 This study aims to develop a person identification (PID) system based on combined use of bronchial breath sounds and speech signals acquired by stethoscope. Two major methods, including support vector machines, and artificial neural networks are evaluated in the task of breath-sound-based PID. With the consideration of convenience, the amount of sound data collected from each person should be as small as possible, and hence the performance of PID may be limited, when the sound data for training the system is insufficient. To boost the performance of PID with sparse training data, this work studies data augmentation (DA) techniques that avoid the system training process from the overfitting problem. In addition, Feature engineering techniques are utilized to find the informative subset of breath sound features which is beneficial for PID. Our experimental data is provided by 16 volunteers, including equal number of male and female participants. In test phase, Both Support vector machine in combined with feature selection and Artificial Neural Networks approaches yielded the comparable accuracies of 98%. Tsai,Wei-Ho 蔡偉和 2019 學位論文 ; thesis 60 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺北科技大學 === 電資國際專班 === 107 === This study aims to develop a person identification (PID) system based on combined use of bronchial breath sounds and speech signals acquired by stethoscope. Two major methods, including support vector machines, and artificial neural networks are evaluated in the task of breath-sound-based PID. With the consideration of convenience, the amount of sound data collected from each person should be as small as possible, and hence the performance of PID may be limited, when the sound data for training the system is insufficient. To boost the performance of PID with sparse training data, this work studies data augmentation (DA) techniques that avoid the system training process from the overfitting problem. In addition, Feature engineering techniques are utilized to find the informative subset of breath sound features which is beneficial for PID. Our experimental data is provided by 16 volunteers, including equal number of male and female participants. In test phase, Both Support vector machine in combined with feature selection and Artificial Neural Networks approaches yielded the comparable accuracies of 98%.
|
author2 |
Tsai,Wei-Ho |
author_facet |
Tsai,Wei-Ho TRAN VAN THUAN TRAN VAN THUAN |
author |
TRAN VAN THUAN TRAN VAN THUAN |
spellingShingle |
TRAN VAN THUAN TRAN VAN THUAN Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
author_sort |
TRAN VAN THUAN |
title |
Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
title_short |
Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
title_full |
Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
title_fullStr |
Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
title_full_unstemmed |
Speech and Breath-Sound-Based Person Identification with Sparse Training Data |
title_sort |
speech and breath-sound-based person identification with sparse training data |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/tpzt27 |
work_keys_str_mv |
AT tranvanthuan speechandbreathsoundbasedpersonidentificationwithsparsetrainingdata AT tranvanthuan speechandbreathsoundbasedpersonidentificationwithsparsetrainingdata AT tranvanthuan yǐshǎoliàngyǔyīnjíhūxīyīnjìnxíngshēnfènshíbié AT tranvanthuan yǐshǎoliàngyǔyīnjíhūxīyīnjìnxíngshēnfènshíbié |
_version_ |
1719177147172519936 |