本文選題：數(shù)字助聽器 + 語音增強(qiáng)��； 參考：《東南大學(xué)》2016年碩士論文

【摘要】：受人口結(jié)構(gòu)老齡化、環(huán)境噪聲污染等因素的影響,越來越多的人聽覺系統(tǒng)受到了損傷。在聽力損失患者的聽力矯正治療中,佩戴助聽器是最安全、最有效的方式,但噪聲污染問題嚴(yán)重影響了助聽器的實(shí)際使用效果,且較之聽力正常人而言,聽損患者在噪聲環(huán)境中的語音理解能力本身就更低。語音增強(qiáng)技術(shù)能有效消除背景噪聲,改善語音質(zhì)量,從而提高患者在噪聲環(huán)境中的語音理解度。在國家自然科學(xué)基金(61301219)和江蘇省自然科學(xué)基金(BK20130241)的資助下,本文在深入理解和研究已有算法的基礎(chǔ)上,重點(diǎn)研究了適用于數(shù)字助聽器的語音增強(qiáng)技術(shù),主要研究工作包括以下幾個部分：(1)介紹了維納濾波語音增強(qiáng)技術(shù),重點(diǎn)研究了基于先驗(yàn)信噪比(Priori SNR)估計的維納濾波法。針對基于Priori SNR估計的維納濾波未能有效提高語音可懂度的缺點(diǎn)進(jìn)行了研究與改進(jìn)：首先,引入了以MMSE為準(zhǔn)則的兩步先驗(yàn)信噪比估計取代原“直接判決”法；其次,針對信噪比為負(fù)的區(qū)域,增益函數(shù)的過高估計會嚴(yán)重降低語音可懂度的問題對增益函數(shù)進(jìn)行了改進(jìn),放大了負(fù)信噪比區(qū)域的噪聲譜,從而降低增益函數(shù)被過高估計的可能性。與原方法的對比實(shí)驗(yàn)驗(yàn)證了改進(jìn)的方法能夠有效的提高語音可懂度。(2)針對基于Priori SNR估計的維納濾波算法計算復(fù)雜度較高的缺點(diǎn),提出了一種計算復(fù)雜度低的數(shù)字助聽器子帶語音增強(qiáng)算法,詳細(xì)介紹了該算法的原理及具體實(shí)現(xiàn)。該方法利用計算各子帶信號功率取代傳統(tǒng)方法中的功率譜的計算,省去了信號時頻域的轉(zhuǎn)換,極大程度的降低了算法的計算復(fù)雜度,滿足了數(shù)字助聽器對實(shí)時性和低功耗的要求。并通過仿真實(shí)驗(yàn)將該算法與改進(jìn)譜減法和基于Priori SNR估計的維納濾波法進(jìn)行了對比分析,驗(yàn)證了算法的有效性。(3)研究了基于方向性麥克風(fēng)的語音增強(qiáng)技術(shù),介紹了方向性麥克風(fēng)用于語音增強(qiáng)的原理及實(shí)現(xiàn)方式,重點(diǎn)對一階自適應(yīng)方向性麥克風(fēng)的原理結(jié)構(gòu)進(jìn)行了研究。方向性麥克風(fēng)只能進(jìn)行初步的噪聲過濾,而子帶語音增強(qiáng)算法對信噪比過低的信號進(jìn)行增強(qiáng)處理時會造成較大的語音失真,針對上述問題,提出了一種方向性麥克風(fēng)與子帶語音增強(qiáng)相結(jié)合的兩步語音增強(qiáng)算法,首先由方向性麥克風(fēng)初步提升信噪比,再由子帶語音增強(qiáng)方法作進(jìn)一步處理,兩者的結(jié)合有效的彌補(bǔ)了彼此的不足,使得最終增強(qiáng)的語音信號質(zhì)量更好。仿真實(shí)驗(yàn)的結(jié)果驗(yàn)證了提出算法的有效性。
[Abstract]:Due to the aging of population structure and environmental noise pollution, more and more people's hearing system is damaged. It is the safest and most effective way to wear hearing aid in hearing loss patients, but the problem of noise pollution seriously affects the actual effect of hearing aid. The speech comprehension ability of hearing impaired patients in noise environment is even lower. Speech enhancement technology can effectively eliminate background noise, improve speech quality and improve the speech comprehension of patients in noisy environment. Supported by the National Natural Science Foundation of China 61301219) and the Natural Science Foundation of Jiangsu Province BK20130241), based on the deep understanding and research of the existing algorithms, this paper focuses on the speech enhancement technology suitable for digital hearing aids. The main research work includes the following parts: 1) the Wiener filter speech enhancement technique is introduced, and the Wiener filtering method based on Priori SNR estimation is emphatically studied. The shortcomings of Wiener filter based on Priori SNR estimation to improve speech intelligibility are studied and improved. Firstly, a two-step prior SNR estimation based on MMSE criterion is introduced to replace the original "direct decision" method. For the region with negative SNR, the gain function can be greatly reduced by overestimation of the gain function, and the noise spectrum of the negative SNR region is enlarged, thus reducing the possibility that the gain function can be overestimated. The comparison experiment with the original method proves that the improved method can effectively improve the speech intelligibility. (2) aiming at the disadvantage of high computational complexity of Wiener filter algorithm based on Priori SNR estimation, the improved method can improve speech intelligibility effectively. A speech enhancement algorithm for digital hearing aids with low computational complexity is proposed. The principle and implementation of the algorithm are introduced in detail. In this method, the power spectrum of each subband signal is calculated instead of the power spectrum of the traditional method, and the time-frequency domain conversion of the signal is eliminated, and the computational complexity of the algorithm is greatly reduced. It meets the requirement of real-time and low power consumption for digital hearing aid. The algorithm is compared with the improved spectral subtraction method and the Wiener filter method based on Priori SNR estimation, and the effectiveness of the algorithm is verified. The speech enhancement technology based on directional microphone is studied. The principle and implementation of directional microphone for speech enhancement are introduced, and the principle structure of the first order adaptive directional microphone is studied. Directional microphones can only carry out initial noise filtering, but subband speech enhancement algorithm will cause large speech distortion when processing signals with too low SNR. In view of the above problems, A two-step speech enhancement algorithm combining directional microphone and subband speech enhancement is proposed. Firstly, the signal to noise ratio (SNR) is initially enhanced by directional microphone, and then further processed by subband speech enhancement method. The combination of the two effectively makes up for each other's shortcomings, making the final enhanced speech signal quality better. Simulation results show the effectiveness of the proposed algorithm.
【學(xué)位授予單位】：東南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TN912.35;TH785.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 余世經(jīng);李冬梅;劉潤生;;一種基于CASA的單通道語音增強(qiáng)方法[J];電聲技術(shù);2014年02期

2 安扣成;;基于先驗(yàn)信噪比估計和增益平滑的語音增強(qiáng)[J];計算機(jī)應(yīng)用;2012年S1期

3 梁瑞宇;奚吉;張學(xué)武;;數(shù)字助聽器發(fā)展現(xiàn)狀及其算法綜述[J];信息化研究;2011年01期

4 張亮;龔衛(wèi)國;;一種改進(jìn)的維納濾波語音增強(qiáng)算法[J];計算機(jī)工程與應(yīng)用;2010年26期

5 楊琳;張建平;顏永紅;;單通道語音增強(qiáng)算法對漢語語音可懂度影響的研究[J];聲學(xué)學(xué)報;2010年02期

6 王青云;趙力;喬杰;鄒采榮;;符合人耳聽覺特征的數(shù)字助聽器子帶響度補(bǔ)償[J];應(yīng)用科學(xué)學(xué)報;2008年06期

7 李蘊(yùn)華;;基于盲源分離的單通道語音信號增強(qiáng)[J];計算機(jī)仿真;2008年07期

8 黃雅婷;陶智;顧濟(jì)華;趙鶴鳴;嚴(yán)冬明;;基于人耳掩蔽效應(yīng)的電子耳蝸語音增強(qiáng)方法[J];計算機(jī)工程;2008年10期

9 曾子臨;;方向性麥克風(fēng)技術(shù)在助聽器中的應(yīng)用[J];中國聽力語言康復(fù)科學(xué)雜志;2006年04期

10 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

，

本文編號：1932461