國立虎尾科技大學 |

Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement./
作者:	Xing, Hua.
面頁冊數:	1 online resource (118 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355393491

Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement.
Xing, Hua.

Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement. - 1 online resource (118 pages)

Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.

Thesis (Ph.D.)--The University of Texas at Dallas, 2017.

Includes bibliographical references

This dissertation focuses on advancing the statistical signal processing and machine learning technologies in speech enhancement tasks. Statistical signal processing and machine learning are the most important and widely used technologies in investigations of speech areas. Although both of the two group technologies have achieved significant success in speech enhancement tasks, they are usually applied independently in the existing solutions. In this dissertation we verified the idea that the combination of techniques from the two domains could further boost the effectiveness in enhancement performance by applying them corporately in two speech enhancement problems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355393491Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement.
LDR:03600ntm a2200349K 4500 001 912433
005 20180608141654.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355393491
035 $a (MiAaPQ)AAI10675334
035 $a (MiAaPQ)0382vireo:186Xing
035 $a AAI10675334
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Xing, Hua. $3 1184790
245 1 0 $a Advancements in Statistical Signal Processing and Machine Learning for Speech Enhancement.
264 0 $c 2017
300 $a 1 online resource (118 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
500 $a Adviser: John H.L. Hansen.
502 $a Thesis (Ph.D.)--The University of Texas at Dallas, 2017.
504 $a Includes bibliographical references
520 $a This dissertation focuses on advancing the statistical signal processing and machine learning technologies in speech enhancement tasks. Statistical signal processing and machine learning are the most important and widely used technologies in investigations of speech areas. Although both of the two group technologies have achieved significant success in speech enhancement tasks, they are usually applied independently in the existing solutions. In this dissertation we verified the idea that the combination of techniques from the two domains could further boost the effectiveness in enhancement performance by applying them corporately in two speech enhancement problems.
520 $a In the first investigated problem, estimating frequency shift estimation in single sideband speech, the existing methods, exclusively based on signal processing, suffered the non-uniqueness issue caused by the periodic characteristic of the voiced speech. To address this issue, a pre-step of uniqueness interval detection is proposed based on the analysis of origins of estimation errors. Three machine learning techniques, GMM-SVM, i-Vector and stacked Autoencoder, are adopted to detect the uniqueness interval in the rst step. A unique feature specially designed to represent the frequency shift property is developed as the input of classifiers . Experimental results veri es the effect of introducing machine learning techniques to the existing solution.
520 $a In the second investigated problem, speech denoising, the linear spectral pair (LSP), an efficient representation for speech which encodes the information of spectral formant location and bandwidth, was adopted as the input of DNN regression architecture along with the conventional log-spectra features. To capture the dynamic property in speech signal, the rst and second derivatives of LSPs are also used. In addition, Auto-LSP, an efficient iterative denoising algorithm is applied as a post-processing to further promote the enhancing result. The effectiveness of the proposed feature and post-processing operation was con rmed by the denoising results in terms of three objective criteria.
520 $a Collectively, the contributions made in these two speech enhancement topics supported the idea that the advantages of signal processing and machine learning could compliment each other to improve the performance of the overall enhancement techniques.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Texas at Dallas. $b Electrical Engineering. $3 1181534
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10675334 $z click for full text (PQDT)