本文選題：語(yǔ)音增強(qiáng)　切入點(diǎn)：變換域　出處：《煙臺(tái)大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：現(xiàn)實(shí)生活和工作中,人們的學(xué)習(xí)、工作及娛樂(lè)活動(dòng)多以語(yǔ)音的傳輸為橋梁,但語(yǔ)音在傳輸過(guò)程中不可避免地會(huì)受到外界噪聲的干擾,從而導(dǎo)致最終接收到的語(yǔ)音信號(hào)質(zhì)量與可懂度下降,嚴(yán)重影響人們的工作和生活品質(zhì)。而要使接收到的語(yǔ)音信號(hào)質(zhì)量和可懂度得到提高、更符合人耳的主觀感受,就必須對(duì)被污染的語(yǔ)音進(jìn)行去噪處理。語(yǔ)音增強(qiáng)即是對(duì)帶噪語(yǔ)音信號(hào)進(jìn)行處理,以盡可能地消除背景噪聲、恢復(fù)出原始語(yǔ)音信號(hào)的過(guò)程。目前,按照語(yǔ)音信號(hào)處理方式的不同可以將語(yǔ)音增強(qiáng)算法分為兩大類(lèi),即時(shí)域語(yǔ)音增強(qiáng)算法和變換域語(yǔ)音增強(qiáng)算法。由于變換域中語(yǔ)音和噪聲能量更集中、兩者之間的特征信息相對(duì)時(shí)域更便于處理,故在變換域中實(shí)現(xiàn)語(yǔ)音增強(qiáng)的算法已成為目前國(guó)內(nèi)外學(xué)者研究的重點(diǎn)。本文研究工作主要在離散余弦變換(DCT,Discrete Cosine Transform)域內(nèi)圍繞基于維納濾波的語(yǔ)音增強(qiáng)技術(shù)展開(kāi),通過(guò)分析和研究現(xiàn)有語(yǔ)音增強(qiáng)算法中增益因子的不足和缺陷,基于語(yǔ)音信號(hào)的統(tǒng)計(jì)模型,采用雙態(tài)維納濾波技術(shù)對(duì)其進(jìn)行改進(jìn),提出了新型的語(yǔ)音增強(qiáng)算法,并從理論和實(shí)驗(yàn)仿真兩個(gè)方面驗(yàn)證了提出算法的性能。本文的主要研究和創(chuàng)新工作具體如下:首先,對(duì)現(xiàn)有變換域中語(yǔ)音增強(qiáng)算法中增益因子的取值問(wèn)題進(jìn)行了研究,利用實(shí)際的語(yǔ)音及噪聲數(shù)據(jù)重點(diǎn)分析了DCT域中純凈語(yǔ)音系數(shù)和噪聲系數(shù)之間的符號(hào)關(guān)系,發(fā)現(xiàn)了傳統(tǒng)維納濾波語(yǔ)音增強(qiáng)技術(shù)中存在的不足;其次,基于前文的實(shí)驗(yàn)分析結(jié)果,采用雙態(tài)維納濾波對(duì)原有算法進(jìn)行了有效改進(jìn),同時(shí)結(jié)合DCT域中常用的高斯及拉普拉斯模型分別對(duì)語(yǔ)音和噪聲信號(hào)進(jìn)行建模,設(shè)計(jì)出了三種統(tǒng)計(jì)模型下的雙態(tài)維納濾波語(yǔ)音增強(qiáng)算法;最后,通過(guò)理論分析和仿真實(shí)驗(yàn)驗(yàn)證了本文研究算法的有效性和優(yōu)越性,同時(shí)對(duì)全文進(jìn)行了總結(jié),并對(duì)所研究語(yǔ)音增強(qiáng)技術(shù)的未來(lái)發(fā)展?fàn)顩r做出了展望。
[Abstract]:In real life and work, people's study, work and entertainment mostly take the voice transmission as the bridge, but in the transmission process, the voice will inevitably be interfered by the external noise. As a result, the final received speech signal quality and intelligibility decline, seriously affecting the quality of people's work and life. To improve the quality and intelligibility of the received speech signal, it is more in line with the subjective feelings of the human ear. Speech enhancement is the process of processing noisy speech signal in order to eliminate background noise as much as possible and recover the original speech signal. According to different speech signal processing methods, speech enhancement algorithms can be divided into two categories, instant speech enhancement algorithm and transform domain speech enhancement algorithm. The characteristic information between the two is easier to process than time domain. Therefore, the implementation of speech enhancement in transform domain has become the focus of scholars at home and abroad. The research work in this paper is mainly focused on Wiener filter based speech enhancement technology in discrete cosine transform (DCT / discrete Cosine transform) domain. By analyzing and studying the deficiency and defect of gain factor in existing speech enhancement algorithms, based on the statistical model of speech signal, a novel speech enhancement algorithm is proposed, which is improved by using two-state Wiener filter technology. The performance of the proposed algorithm is verified by theoretical and experimental simulation. The main research and innovation work of this paper is as follows: firstly, the gain factor in the existing speech enhancement algorithm in transform domain is studied. The symbolic relationship between pure speech coefficients and noise coefficients in DCT domain is analyzed by using actual speech and noise data, and the shortcomings of traditional Wiener filter speech enhancement techniques are found. The two-state Wiener filter is used to improve the original algorithm effectively. At the same time, combined with Gao Si and Laplace models in DCT domain, the speech and noise signals are modeled, respectively. This paper designs three kinds of two-state Wiener filter speech enhancement algorithm under three statistical models. Finally, through theoretical analysis and simulation experiments, the validity and superiority of this algorithm are verified, and the full text is summarized. The future development of the speech enhancement technology is prospected.
【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(lèi)號(hào)】：TN912.35

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 徐文超;王光艷;陳雷;;改進(jìn)的變步長(zhǎng)最小均方誤差電子耳蝸語(yǔ)音增強(qiáng)算法[J];計(jì)算機(jī)應(yīng)用;2017年04期

2 孟欣;馬建芬;張雪英;;改進(jìn)的參數(shù)自適應(yīng)的維納濾波語(yǔ)音增強(qiáng)算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2017年03期

3 米建偉;方曉莉;仇原鷹;;非平穩(wěn)背景噪聲下聲音信號(hào)增強(qiáng)技術(shù)[J];儀器儀表學(xué)報(bào);2017年01期

4 張素貞;唐加能;梁瑞宇;;仿聽(tīng)覺(jué)掩蔽效應(yīng)的助聽(tīng)器語(yǔ)音增強(qiáng)算法[J];電子器件;2016年03期

5 葉琪;陶亮;周健;王華彬;;基于聯(lián)合失真控制的子空間語(yǔ)音增強(qiáng)算法[J];聲學(xué)技術(shù);2016年03期

6 寧礦鳳;王景芳;;DCT域維納濾波語(yǔ)音增強(qiáng)[J];計(jì)算機(jī)工程與應(yīng)用;2015年08期

7 黃蘇雨;梁聲灼;黃蘇園;;語(yǔ)音增強(qiáng)方法綜述[J];計(jì)算機(jī)與現(xiàn)代化;2007年03期

8 洪銳;郭繼昌;;基于DCT與神經(jīng)網(wǎng)絡(luò)的語(yǔ)音增強(qiáng)方法[J];電子測(cè)量技術(shù);2006年06期

9 歐世峰;趙曉暉;顧海軍;;基于DCT與維納濾波的單通道語(yǔ)音增強(qiáng)算法[J];通信學(xué)報(bào);2006年10期

10 劉塞立;離散余弦變換與離散傅里葉變換之間的關(guān)系[J];西安石油學(xué)院學(xué)報(bào)(自然科學(xué)版);1995年01期

相關(guān)博士學(xué)位論文 前1條

1 歐世峰;變換域語(yǔ)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8條

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

2 時(shí)勇強(qiáng);基于深度神經(jīng)網(wǎng)絡(luò)的語(yǔ)音增強(qiáng)算法研究[D];北京工業(yè)大學(xué);2016年

3 王永杰;基于麥克風(fēng)陣列的語(yǔ)音增強(qiáng)算法研究[D];西安電子科技大學(xué);2014年

4 于文慧;基于短時(shí)譜估計(jì)的MMSE語(yǔ)音增強(qiáng)算法研究[D];吉林大學(xué);2012年

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

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

7 高留洋;低信噪比下的語(yǔ)音增強(qiáng)方法研究[D];解放軍信息工程大學(xué);2010年

8 章旭景;基于卡爾曼濾波的語(yǔ)音增強(qiáng)算法研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2009年

，

本文編號(hào)：1588725