本文選題：語音增強(qiáng)　切入點(diǎn)：先驗(yàn)信噪比　出處：《煙臺(tái)大學(xué)》2017年碩士論文

【摘要】：語音是人與人以及人與機(jī)器間交流、互通最為便捷的方式之一,但語音信號(hào)在傳輸和處理的過程中,不可避免地要受到外界背景噪聲的干擾或損傷,從而導(dǎo)致接受者較難理解和感知,同時(shí)也會(huì)大大降低語音信號(hào)處理系統(tǒng)的整體性能。語音增強(qiáng)的目的在于去除被污染語音中的噪聲信號(hào),進(jìn)而增強(qiáng)語音處理、通信設(shè)備的魯棒性,提高語音的質(zhì)量和可懂度。本文的研究工作主要圍繞語音增強(qiáng)技術(shù)中的先驗(yàn)信噪比估計(jì)問題開展。眾所周知,先驗(yàn)信噪比是語音增強(qiáng)技術(shù)中的核心參數(shù),對(duì)于其估計(jì)的合理性和準(zhǔn)確度將在較大程度上影響語音增強(qiáng)系統(tǒng)的總體輸出性能。論文在研究了多種先驗(yàn)信噪比估計(jì)算法的基礎(chǔ)上,詳細(xì)分析了直接判決算法中平滑因子的取值對(duì)于系統(tǒng)整體增強(qiáng)效果的影響,通過設(shè)置耦合因子將兩個(gè)不同性能的直接判決算法進(jìn)行組合,提出了一種新型的先驗(yàn)信噪比估計(jì)算法,并經(jīng)過理論分析和仿真實(shí)驗(yàn)驗(yàn)證了該算法的估計(jì)效果。論文的研究和創(chuàng)新工作主要包括:首先,闡述、分析了變換域語音增強(qiáng)算法的特點(diǎn)以及先驗(yàn)信噪比參數(shù)對(duì)于算法整體輸出性能的影響,并對(duì)現(xiàn)有多種先驗(yàn)信噪比估計(jì)算法的基本原理和優(yōu)缺點(diǎn)進(jìn)行了說明和分析。其次,針對(duì)最為常用的直接判決先驗(yàn)信噪比估計(jì)算法進(jìn)行了詳盡分析和研究,采用對(duì)數(shù)似然比和幅度分布直方圖等客觀評(píng)判標(biāo)準(zhǔn)研究了直接判決算法下語音增強(qiáng)系統(tǒng)輸出信號(hào)的失真及音樂噪聲殘留情況,并根據(jù)其實(shí)驗(yàn)結(jié)果給出了算法總體輸出性能隨平滑因子變化的規(guī)律,進(jìn)而確定了音樂噪聲殘留量較低及語音失真程度較小時(shí)的平滑因子最優(yōu)取值。再次,依據(jù)對(duì)平滑因子選值問題的研究結(jié)果,通過引入耦合因子將兩個(gè)具有不同性能和特點(diǎn)的直接判決算法進(jìn)行自適應(yīng)耦合,并基于最小均方誤差理論推導(dǎo)獲取了耦合因子的最優(yōu)值,從而提出了一種具有耦合結(jié)構(gòu)的先驗(yàn)信噪比估計(jì)新型算法。最后,在多種噪聲環(huán)境及信噪比條件下對(duì)論文提出算法的性能進(jìn)行了仿真驗(yàn)證,其結(jié)果有效表明了提出算法的優(yōu)良性能。在此基礎(chǔ)上對(duì)全文進(jìn)行了總結(jié),并對(duì)語音增強(qiáng)技術(shù)中先驗(yàn)信噪比估計(jì)問題的未來研究方向進(jìn)行了展望。
[Abstract]:Voice is one of the most convenient ways to communicate and communicate between people and machines, but in the process of transmission and processing, it is inevitable to be disturbed or damaged by background noise. Therefore, it is difficult for the receiver to understand and perceive, and at the same time will greatly reduce the overall performance of the speech signal processing system. The purpose of speech enhancement is to remove the noise signal from the contaminated speech, and then to enhance the speech processing. The research work in this paper focuses on the estimation of prior signal-to-noise ratio in speech enhancement technology. As we all know, prior signal-to-noise ratio (SNR) is the core parameter in speech enhancement technology. The rationality and accuracy of the estimation will greatly affect the overall output performance of the speech enhancement system. The influence of the smoothing factor on the overall enhancement effect of the system is analyzed in detail. Two direct decision algorithms with different performance are combined by setting the coupling factor. A new priori signal-to-noise ratio (SNR) estimation algorithm is proposed, and its effect is verified by theoretical analysis and simulation experiments. The characteristics of speech enhancement algorithm in transform domain and the influence of prior signal-to-noise ratio (SNR) parameters on the overall output performance of the algorithm are analyzed, and the basic principles, advantages and disadvantages of various prior SNR estimation algorithms are explained and analyzed. The most commonly used direct decision prior signal-to-noise ratio estimation algorithm is analyzed and studied in detail. The distortion of output signal and the residual of music noise in speech enhancement system under direct decision algorithm are studied by using logarithmic likelihood ratio and amplitude distribution histogram. According to the experimental results, the rule that the overall output performance of the algorithm varies with the smoothing factor is given, and then the optimal value of the smoothing factor with low residual music noise and low speech distortion is determined. Based on the results of the study on smoothing factor selection, two direct decision algorithms with different performance and characteristics are coupled adaptively by introducing the coupling factor, and the optimal value of the coupling factor is derived based on the minimum mean square error theory. A new transcendental SNR estimation algorithm with coupling structure is proposed. Finally, the performance of the proposed algorithm is verified by simulation under various noise environments and SNR conditions. The results show the excellent performance of the proposed algorithm. Based on this, the paper summarizes the whole paper and looks forward to the future research direction of the prior signal-to-noise ratio estimation in speech enhancement technology.
【學(xué)位授予單位】：煙臺(tái)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN912.35

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 沈鎖金;劉偉;魏靜;;基于動(dòng)量項(xiàng)先驗(yàn)信噪比估計(jì)的語音增強(qiáng)算法[J];電聲技術(shù);2017年01期

2 王棟;賈海蓉;;改進(jìn)相位譜補(bǔ)償?shù)恼Z音增強(qiáng)算法[J];西安電子科技大學(xué)學(xué)報(bào);2017年03期

3 張素貞;唐加能;梁瑞宇;;仿聽覺掩蔽效應(yīng)的助聽器語音增強(qiáng)算法[J];電子器件;2016年03期

4 陳勝;徐巖;;基于人耳感知掩蔽效應(yīng)的子空間語音增強(qiáng)算法研究[J];電子質(zhì)量;2014年12期

5 鄭成詩(shī);周];李曉東;;基于聯(lián)合語音出現(xiàn)概率的先驗(yàn)信噪比估計(jì)算法[J];電子與信息學(xué)報(bào);2008年07期

6 李雪耀;謝華;張汝波;;基于離散余弦變換的語音增強(qiáng)[J];哈爾濱工程大學(xué)學(xué)報(bào);2007年02期

7 鄒霞;陳亮;張雄偉;;基于Gamma語音模型的語音增強(qiáng)算法[J];通信學(xué)報(bào);2006年10期

8 吳周橋,談新權(quán);基于子空間方法的語音增強(qiáng)算法研究[J];聲學(xué)與電子工程;2005年03期

相關(guān)博士學(xué)位論文 前2條

1 徐勇;基于深層神經(jīng)網(wǎng)絡(luò)的語音增強(qiáng)方法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2015年

2 歐世峰;變換域語音增強(qiáng)算法的研究[D];吉林大學(xué);2008年

相關(guān)碩士學(xué)位論文 前9條

1 魏泉水;基于深度神經(jīng)網(wǎng)絡(luò)的語音增強(qiáng)算法研究[D];南京大學(xué);2016年

2 翟振輝;基于噪聲幅度譜估計(jì)的單通道語音增強(qiáng)算法研究[D];煙臺(tái)大學(xué);2016年

3 徐志奪;基于小波變換的語音增強(qiáng)算法研究[D];哈爾濱工程大學(xué);2013年

4 楊勇;基于統(tǒng)計(jì)模型和貝葉斯估計(jì)的語音增強(qiáng)算法研究[D];湖南大學(xué);2012年

5 王顯云;統(tǒng)計(jì)模型語音增強(qiáng)算法研究[D];煙臺(tái)大學(xué);2012年

6 孫晉松;語音增強(qiáng)算法的研究及改進(jìn)[D];山東大學(xué);2009年

7 安文彥;實(shí)時(shí)語音增強(qiáng)的研究及其DSP系統(tǒng)實(shí)現(xiàn)[D];電子科技大學(xué);2009年

8 金學(xué)驥;語音增強(qiáng)算法的研究與實(shí)現(xiàn)[D];浙江大學(xué);2005年

9 陶智;基于人耳聽覺掩蔽效應(yīng)的語音增強(qiáng)的研究[D];蘇州大學(xué);2003年

，

本文編號(hào)：1671289