東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Estimation of glottal source feature...

Torres, Juan Felix.

FindBook

Google Book

Amazon

博客來

Estimation of glottal source features from the spectral envelope of the acoustic speech signal.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Estimation of glottal source features from the spectral envelope of the acoustic speech signal./
作者:	Torres, Juan Felix.
面頁冊數:	217 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-10, Section: B, page: 6344.
Contained By:	Dissertation Abstracts International71-10B.
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3425159
ISBN:	9781124258867

Estimation of glottal source features from the spectral envelope of the acoustic speech signal.
Torres, Juan Felix.

Estimation of glottal source features from the spectral envelope of the acoustic speech signal. - 217 p.

Source: Dissertation Abstracts International, Volume: 71-10, Section: B, page: 6344.

Thesis (Ph.D.)--Georgia Institute of Technology, 2010.

Speech communication encompasses diverse types of information, including phonetics, affective state, voice quality, and speaker identity. From a speech production standpoint, the acoustic speech signal can be mainly divided into glottal source and vocal tract components, which play distinct roles in rendering the various types of information it contains. Most deployed speech analysis systems, however, do not explicitly represent these two components as distinct entities, as their joint estimation from the acoustic speech signal becomes an ill-defined blind deconvolution problem. Nevertheless, because of the desire to understand glottal behavior and how it relates to perceived voice quality, there has been continued interest in explicitly estimating the glottal component of the speech signal. To this end, several inverse filtering (IF) algorithms have been proposed, but they are unreliable in practice because of the blind formulation of the separation problem. In an effort to develop a method that can bypass the challenging IF process, this thesis proposes a new glottal source information extraction method that relies on supervised machine learning to transform smoothed spectral representations of speech, which are already used in some of the most widely deployed and successful speech analysis applications, into a set of glottal source features. A transformation method based on Gaussian mixture regression (GMR) is presented and compared to current IF methods in terms of feature similarity, reliability, and speaker discrimination capability on a large speech corpus, and potential representations of the spectral envelope of speech are investigated for their ability represent glottal source variation in a predictable manner. The proposed system was found to produce glottal source features that reasonably matched their IF counterparts in many cases, while being less susceptible to spurious errors. The development of the proposed method entailed a study into the aspects of glottal source information that are already contained within the spectral features commonly used in speech analysis, yielding an objective assessment regarding the expected advantages of explicitly using glottal information extracted from the speech signal via currently available IF methods, versus the alternative of relying on the glottal source information that is implicitly contained in spectral envelope representations.

ISBN: 9781124258867Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Estimation of glottal source features from the spectral envelope of the acoustic speech signal.
LDR:03360nam 2200289 4500 001 1400135
005 20111005095557.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124258867
035 $a (UMI)AAI3425159
035 $a AAI3425159
040 $a UMI $c UMI
100 1 $a Torres, Juan Felix. $3 1679157
245 1 0 $a Estimation of glottal source features from the spectral envelope of the acoustic speech signal.
300 $a 217 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-10, Section: B, page: 6344.
500 $a Adviser: Elliot Moore.
502 $a Thesis (Ph.D.)--Georgia Institute of Technology, 2010.
520 $a Speech communication encompasses diverse types of information, including phonetics, affective state, voice quality, and speaker identity. From a speech production standpoint, the acoustic speech signal can be mainly divided into glottal source and vocal tract components, which play distinct roles in rendering the various types of information it contains. Most deployed speech analysis systems, however, do not explicitly represent these two components as distinct entities, as their joint estimation from the acoustic speech signal becomes an ill-defined blind deconvolution problem. Nevertheless, because of the desire to understand glottal behavior and how it relates to perceived voice quality, there has been continued interest in explicitly estimating the glottal component of the speech signal. To this end, several inverse filtering (IF) algorithms have been proposed, but they are unreliable in practice because of the blind formulation of the separation problem. In an effort to develop a method that can bypass the challenging IF process, this thesis proposes a new glottal source information extraction method that relies on supervised machine learning to transform smoothed spectral representations of speech, which are already used in some of the most widely deployed and successful speech analysis applications, into a set of glottal source features. A transformation method based on Gaussian mixture regression (GMR) is presented and compared to current IF methods in terms of feature similarity, reliability, and speaker discrimination capability on a large speech corpus, and potential representations of the spectral envelope of speech are investigated for their ability represent glottal source variation in a predictable manner. The proposed system was found to produce glottal source features that reasonably matched their IF counterparts in many cases, while being less susceptible to spurious errors. The development of the proposed method entailed a study into the aspects of glottal source information that are already contained within the spectral features commonly used in speech analysis, yielding an objective assessment regarding the expected advantages of explicitly using glottal information extracted from the speech signal via currently available IF methods, versus the alternative of relying on the glottal source information that is implicitly contained in spectral envelope representations.
590 $a School code: 0078.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Physics, Acoustics. $3 1019086
690 $a 0544
690 $a 0800
690 $a 0986
710 2 $a Georgia Institute of Technology. $3 696730
773 0 $t Dissertation Abstracts International $g 71-10B.
790 1 0 $a Moore, Elliot, $e advisor
790 $a 0078
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3425159