Voice Activity Detection based on Harmonic Structure in Keyword Listening Application

碩士 === 國立交通大學 === 電控工程研究所 === 103 === This thesis proposes a new voice activity detection (VAD) algorithm which is based on harmonic structure feature in keyword listening application. Harmonic structure is a feature that using the periodicity of energy in frequency domain. This approach searches th...

Full description

Bibliographic Details
Main Authors: Chien, Yu-Hsuan, 簡佑軒
Other Authors: Hu Jwu-Sheng
Format: Others
Language:zh-TW
Published: 2014
Online Access:http://ndltd.ncl.edu.tw/handle/11510830911622734593
id ndltd-TW-103NCTU5449020
record_format oai_dc
spelling ndltd-TW-103NCTU54490202016-08-28T04:12:41Z http://ndltd.ncl.edu.tw/handle/11510830911622734593 Voice Activity Detection based on Harmonic Structure in Keyword Listening Application 應用於關鍵字監聽之諧波結構語音活動偵測演算法 Chien, Yu-Hsuan 簡佑軒 碩士 國立交通大學 電控工程研究所 103 This thesis proposes a new voice activity detection (VAD) algorithm which is based on harmonic structure feature in keyword listening application. Harmonic structure is a feature that using the periodicity of energy in frequency domain. This approach searches the obvious part of harmonic structure in frequency domain as speech feature, and check the continuity of harmonic structure in time domain as VAD decision rule. The proposed algorithm is tested under different types of non-stationary noises and different SNR condition. Experimental results demonstrate its advantages over other VADs such as G.729, long-term spectral divergence (LTSD) and Gaussian mixture model (GMM). Hu Jwu-Sheng 胡竹生 2014 學位論文 ; thesis 59 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立交通大學 === 電控工程研究所 === 103 === This thesis proposes a new voice activity detection (VAD) algorithm which is based on harmonic structure feature in keyword listening application. Harmonic structure is a feature that using the periodicity of energy in frequency domain. This approach searches the obvious part of harmonic structure in frequency domain as speech feature, and check the continuity of harmonic structure in time domain as VAD decision rule. The proposed algorithm is tested under different types of non-stationary noises and different SNR condition. Experimental results demonstrate its advantages over other VADs such as G.729, long-term spectral divergence (LTSD) and Gaussian mixture model (GMM).
author2 Hu Jwu-Sheng
author_facet Hu Jwu-Sheng
Chien, Yu-Hsuan
簡佑軒
author Chien, Yu-Hsuan
簡佑軒
spellingShingle Chien, Yu-Hsuan
簡佑軒
Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
author_sort Chien, Yu-Hsuan
title Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
title_short Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
title_full Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
title_fullStr Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
title_full_unstemmed Voice Activity Detection based on Harmonic Structure in Keyword Listening Application
title_sort voice activity detection based on harmonic structure in keyword listening application
publishDate 2014
url http://ndltd.ncl.edu.tw/handle/11510830911622734593
work_keys_str_mv AT chienyuhsuan voiceactivitydetectionbasedonharmonicstructureinkeywordlisteningapplication
AT jiǎnyòuxuān voiceactivitydetectionbasedonharmonicstructureinkeywordlisteningapplication
AT chienyuhsuan yīngyòngyúguānjiànzìjiāntīngzhīxiébōjiégòuyǔyīnhuódòngzhēncèyǎnsuànfǎ
AT jiǎnyòuxuān yīngyòngyúguānjiànzìjiāntīngzhīxiébōjiégòuyǔyīnhuódòngzhēncèyǎnsuànfǎ
_version_ 1718381072830431232