本文選題：語(yǔ)音增強(qiáng) + 高階累積量�。� 參考：《電子科技大學(xué)》2014年碩士論文

【摘要】：語(yǔ)音增強(qiáng)作為通信領(lǐng)域中一項(xiàng)重要技術(shù)手段,隨著通信技術(shù)的快速發(fā)展,它在語(yǔ)音識(shí)別、降噪和語(yǔ)音編碼等方面發(fā)揮著越來(lái)越重要的作用,成為了近30年中語(yǔ)音處理領(lǐng)域的熱點(diǎn)話題。它以提高語(yǔ)言信號(hào)信噪比,改善語(yǔ)音質(zhì)量為目標(biāo),進(jìn)而提高語(yǔ)音信號(hào)的舒適度與可懂度,有著十分重要的實(shí)用意義。語(yǔ)音信號(hào)數(shù)字模型是語(yǔ)音信號(hào)處理的基礎(chǔ),模型的準(zhǔn)確性將直接影響到語(yǔ)音信號(hào)的后續(xù)處理。本文將建立一個(gè)全極點(diǎn)模型,該模型結(jié)構(gòu)簡(jiǎn)單易于實(shí)現(xiàn)。語(yǔ)言增強(qiáng)算法的重點(diǎn)是對(duì)語(yǔ)音信號(hào)模型和噪聲做參數(shù)估計(jì),模型參數(shù)是卡爾曼濾波算法基礎(chǔ)。噪聲參數(shù)估計(jì)主要是通過(guò)VAD算法對(duì)語(yǔ)音作有效檢測(cè),在信號(hào)無(wú)聲段通過(guò)LPC自相關(guān)法直接估計(jì)。接著使用一些常用的參數(shù)估計(jì)算法,如極大似然函數(shù)法、Burg算法等,進(jìn)行仿真實(shí)驗(yàn)。但低信噪比下,這些方法將誤差增大,變的不穩(wěn)定。所以本文在此基礎(chǔ)上應(yīng)用了基于高階累積量的參數(shù)估計(jì)算法,根據(jù)其特性可知純凈語(yǔ)音信號(hào)與帶噪信號(hào)的高階累積量相等。根據(jù)這一事實(shí),我們便可以把AR模型通過(guò)高階累積量表示,即MYW方程。而MYW方程的求解方法主要有輔助變量法、LMS算法。通過(guò)改進(jìn)LMS算法,本文提出了共軛梯度算法,通過(guò)實(shí)驗(yàn)證明,效果與LMS算法類(lèi)似,但可以簡(jiǎn)化運(yùn)算。最后通過(guò)卡爾曼濾波,實(shí)現(xiàn)語(yǔ)音增強(qiáng)。通過(guò)仿真實(shí)驗(yàn)結(jié)果分析,高階累積量結(jié)合共軛梯度算法可以很好的實(shí)現(xiàn)語(yǔ)言增強(qiáng),不僅提高了增強(qiáng)算法的適用范圍同時(shí)簡(jiǎn)化了運(yùn)算。最后,為了驗(yàn)證算法的可行性、實(shí)時(shí)性,本文設(shè)計(jì)了硬件平臺(tái);利用芯片TMS320VC5402作處理器,TLV320AIC23B采集音頻信號(hào),STC89LE58RD+作控制器,這樣不僅節(jié)約了成本,同時(shí)提高了效率。
[Abstract]:As an important technical means in the field of communication, speech enhancement plays a more and more important role in speech recognition, noise reduction and speech coding with the rapid development of communication technology. It has become a hot topic in the field of speech processing in the past 30 years. It aims at improving the signal-to-noise ratio (SNR) and speech quality of speech signals, and then improves the comfort and intelligibility of speech signals, which is of great practical significance. Speech signal digital model is the basis of speech signal processing, the accuracy of the model will directly affect the subsequent processing of speech signal. In this paper, a full pole model is established, which is simple and easy to implement. The emphasis of speech enhancement algorithm is to estimate the parameters of speech signal model and noise, and the model parameters are the basis of Kalman filter algorithm. Noise parameter estimation mainly uses VAD algorithm to detect speech effectively, and LPC autocorrelation method is used to estimate the noise parameter directly in the silent segment of the signal. Then some commonly used parameter estimation algorithms, such as the maximum likelihood function method and Burg algorithm, are used to carry out simulation experiments. However, at low SNR, these methods will increase the error and become unstable. In this paper, a parameter estimation algorithm based on high order cumulant is applied. According to its characteristics, the high order cumulant of pure speech signal and noisy signal is equal. According to this fact, we can express AR model by higher order cumulant, that is, MYW equation. The main methods for solving MYW equation are the auxiliary variable method and the LMS algorithm. The conjugate gradient algorithm is proposed by improving the LMS algorithm. It is proved by experiments that the effect is similar to that of the LMS algorithm, but the operation can be simplified. Finally, speech enhancement is realized by Kalman filter. The simulation results show that high order cumulant combined with conjugate gradient algorithm can achieve language enhancement, which not only improves the application range of the enhancement algorithm, but also simplifies the operation. Finally, in order to verify the feasibility and real time of the algorithm, this paper designs a hardware platform and uses chip TMS320VC5402 as the controller to collect audio signal from TLV320AIC23B, which not only saves the cost but also improves the efficiency.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN912.35

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 高鷹,謝勝利;一種變步長(zhǎng)LMS自適應(yīng)濾波算法及分析[J];電子學(xué)報(bào);2001年08期

2 崔恒志;王，

本文編號(hào)：1823022