國立高雄大學圖資館 |

Language: English

Back to Search results for [ author_sort:"zhang, wei." ]

Speech enhancement based on perceptu...

University of Ottawa (Canada).

Speech enhancement based on perceptual loudness and statistical models of speech.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Speech enhancement based on perceptual loudness and statistical models of speech.
Author:	Zhang, Wei.
Description:	292 p.
Notes:	Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3866.
Contained By:	Dissertation Abstracts International71-06B.
Subject:	Engineering, Electronics and Electrical.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR61400
ISBN:	9780494614006

Speech enhancement based on perceptual loudness and statistical models of speech.
Zhang, Wei.

Speech enhancement based on perceptual loudness and statistical models of speech. - 292 p.

Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3866.

Thesis (Ph.D.)--University of Ottawa (Canada), 2009.

This dissertation is concerned with speech enhancement based on the statistical and loudness models. We will study the field of speech enhancement with the objective of improving the quality of speech signals in noisy environments.

ISBN: 9780494614006Subjects--Topical Terms:

226981
Engineering, Electronics and Electrical.

Speech enhancement based on perceptual loudness and statistical models of speech.
LDR:03154nmm 2200289 4500 001 280827
005 20110119095004.5
008 110301s2009 ||||||||||||||||| ||eng d
020 $a 9780494614006
035 $a (UMI)AAINR61400
035 $a AAINR61400
040 $a UMI $c UMI
100 1 $a Zhang, Wei. $3 281236
245 1 0 $a Speech enhancement based on perceptual loudness and statistical models of speech.
300 $a 292 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-06, Section: B, page: 3866.
502 $a Thesis (Ph.D.)--University of Ottawa (Canada), 2009.
520 $a This dissertation is concerned with speech enhancement based on the statistical and loudness models. We will study the field of speech enhancement with the objective of improving the quality of speech signals in noisy environments.
520 $a First, speech enhancement based on the Laplacian model for speech signais is reviewed. The performance is shown to be limited by the accuracy of the Laplacian parameter estimation in the noisy environment. A recursive version is proposed to estimate the Laplacian model parameters using the enhanced speech and then use these estimated parameters to re-enhance the original noisy speech again. This approach achieves better parameter estimation and hence further improvements of speech quality.
520 $a Next, loudness models for speech are reviewed. Considering that it describes the human hearing system better than the spectrum, the fundamental approaches of spectral subtraction are extended to the loudness domain. We propose the loudness subtraction approach. The tests are done for subtraction with different a values in the loudness model. Simulations show that the quality of enhanced speech can be optimized by choosing the appropriate a for a given input SNR. Thus, an adaptive-a subtraction model is proposed. The simulations show it can further improve the performance of spectral subtraction.
520 $a Then, the proposed loudness subtraction with fixed a is shown to provide better results overall than the classical spectral subtraction, even though noise residue and unpleasant artifacts are still high in the enhanced signal. Loudness over-subtraction is then proposed to further reduce these artifacts/noise. Extensive simulation studies are conducted showing clear improvement over other subtraction type approaches.
520 $a Finally, we proposed a Maximum Likelihood-based (ML) speech enhancement algorithm in the loudness domain. It is an optimal speech enhancement algorithm based on the ML criteria in the loudness domain, given the loudness of the noisy speech and the noise estimate. The Laplacian model and the Gaussian model of speech are used separately for comparison. Both approaches shows significant improvement of quality. It is shown that the Laplacian model leads to better preservation of the speech and the Gaussian model leads to better noise reduction.
590 $a School code: 0918.
650 4 $a Engineering, Electronics and Electrical. $3 226981
690 $a 0544
710 2 $a University of Ottawa (Canada). $3 492961
773 0 $t Dissertation Abstracts International $g 71-06B.
790 $a 0918
791 $a Ph.D.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=NR61400