【摘要】：本文針對(duì)機(jī)載噪聲環(huán)境下的語(yǔ)音增強(qiáng),以降低乃至消弱單頻噪聲和克服特定噪聲為目的,借助語(yǔ)音端點(diǎn)檢測(cè)、自適應(yīng)LMS算法、語(yǔ)音增強(qiáng)算法提高語(yǔ)音質(zhì)量,并利用DSP軟硬件處理平臺(tái)進(jìn)行了降噪算法移植,主要內(nèi)容如下:1、概述了語(yǔ)音信號(hào)處理的有關(guān)理論,分析、討論及仿真了有關(guān)語(yǔ)音增強(qiáng)算法,介紹了用于評(píng)測(cè)語(yǔ)音質(zhì)量和語(yǔ)音失真程度的主客觀評(píng)價(jià)指標(biāo)。2、針對(duì)機(jī)載系統(tǒng)的單頻(窄帶)噪聲進(jìn)行了仿真模擬,設(shè)置兩個(gè)高低門(mén)限閾值和一個(gè)過(guò)零率門(mén)限閾值區(qū)分出單頻干擾信號(hào),與改進(jìn)譜熵函數(shù)結(jié)合的方式對(duì)語(yǔ)音端點(diǎn)檢測(cè),然后利用多窗譜估計(jì)譜減法濾除部分噪聲,同時(shí)對(duì)機(jī)載的單音檢測(cè)信號(hào)提出一種改進(jìn)的歸一化自適應(yīng)LMS變步長(zhǎng)濾波算法,利用濾波器輸入輸出端的誤差最小以及算法的收斂速度來(lái)判定單音降噪的效果,然后將消除單音的語(yǔ)音數(shù)據(jù)存儲(chǔ)在緩沖池等待輸出。3、針對(duì)機(jī)載環(huán)境的低頻或高頻分量的噪聲譜估計(jì),利用改進(jìn)語(yǔ)音增強(qiáng)殘差的IMCRA算法,對(duì)急劇變化的非平穩(wěn)噪聲實(shí)現(xiàn)快速跟蹤和更新,通過(guò)語(yǔ)音存在概率對(duì)語(yǔ)音幀設(shè)置判決門(mén)限區(qū)分無(wú)聲段和語(yǔ)音段來(lái)減少噪聲的過(guò)估計(jì),有效降低延時(shí)和偏差;為了降低音樂(lè)噪聲借助改進(jìn)LogMMSE算法估計(jì)先驗(yàn)信噪比,對(duì)語(yǔ)音功率譜平滑處理,基于時(shí)頻分割的理想二值掩蔽消除低于信噪比閾值部分,最后獲取增強(qiáng)的語(yǔ)音信號(hào),并給出改進(jìn)算法的MATLAB仿真及數(shù)據(jù)分析。4、基于TMS320VC5416搭建了 DSP的軟硬件平臺(tái)開(kāi)展語(yǔ)音降噪算法移植,分析了有關(guān)譜減和LMS降噪算法的移植思想,仿真結(jié)果表明可改善語(yǔ)音質(zhì)量。
[Abstract]:Aiming at speech enhancement in airborne noise environment, the purpose of this paper is to reduce or even reduce the single frequency noise and to overcome the specific noise. With the help of speech endpoint detection, adaptive LMS algorithm and speech enhancement algorithm, the speech quality is improved. The noise reduction algorithm is transplanted by using the DSP software and hardware processing platform. The main contents are as follows: 1. The theory, analysis, simulation and simulation of speech signal processing are summarized, and the speech enhancement algorithm is discussed and simulated. This paper introduces the subjective and objective evaluation index .2which is used to evaluate the speech quality and the degree of speech distortion, and simulates the single frequency (narrowband) noise of the airborne system. Two high and low threshold thresholds and a zero crossing threshold are set to distinguish the single frequency interference signal. The speech endpoint is detected by combining with the improved spectral entropy function, and then the partial noise is filtered by multi-window spectral estimation spectral subtraction. At the same time, an improved normalized adaptive LMS variable step size filtering algorithm is proposed for airborne single-tone detection signals. The minimum error at the input and output end of the filter and the convergence speed of the algorithm are used to determine the effect of single-tone noise reduction. Then the single-tone data is stored in the buffer pool waiting for output .3. the improved speech enhancement residual IMCRA algorithm is used to estimate the noise spectrum of the low-frequency or high-frequency components in the airborne environment. The fast tracking and updating of the rapidly changing non-stationary noise is realized, and the decision threshold of speech frame is set to distinguish the silent segment from the speech segment to reduce the over-estimation of the noise, and the delay and deviation are effectively reduced. In order to reduce music noise and estimate prior signal-to-noise ratio (SNR) by using improved LogMMSE algorithm, an ideal binary masking based on time-frequency segmentation is used to eliminate the threshold part of SNR, and then the enhanced speech signal is obtained. The MATLAB simulation and data analysis of the improved algorithm are given. The software and hardware platform of DSP based on TMS320VC5416 is built to transplant the speech noise reduction algorithm. The transplant ideas of spectrum reduction and LMS denoising algorithm are analyzed. The simulation results show that the speech quality can be improved.
【學(xué)位授予單位】：華中師范大學(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5條

1 龐亮;陳亮;張翼鵬;黃清泉;;基于增益字典查詢的語(yǔ)音增強(qiáng)算法[J];計(jì)算機(jī)科學(xué);2015年10期

2 房安棟;劉軍萬(wàn);;復(fù)雜背景下聲紋識(shí)別系統(tǒng)的研究方法綜述[J];電子世界;2013年03期

3 鄧艷容;景新幸;楊海燕;楊運(yùn)澤;;語(yǔ)音端點(diǎn)檢測(cè)研究[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2012年06期

4 姚永強(qiáng);易本順;姚遠(yuǎn);;航空噪聲背景下的語(yǔ)音端點(diǎn)檢測(cè)和語(yǔ)音增強(qiáng)[J];電聲技術(shù);2006年01期

5 蔡斌,郭英,李宏偉,龔成;一種改進(jìn)型MMSE語(yǔ)音增強(qiáng)方法[J];信號(hào)處理;2004年01期

相關(guān)碩士學(xué)位論文 前6條

1 羅路;基于ARM平臺(tái)的語(yǔ)音降噪算法的研究與實(shí)現(xiàn)[D];山東大學(xué);2015年

2 張海南;非平穩(wěn)噪聲環(huán)境中的語(yǔ)音增強(qiáng)技術(shù)研究[D];電子科技大學(xué);2015年

3 康康;基于雙通道DSP+FPGA的數(shù)字信號(hào)處理系統(tǒng)[D];西安電子科技大學(xué);2014年

4 袁問(wèn)渠;混合編碼方式下語(yǔ)音增強(qiáng)方法的研究與實(shí)現(xiàn)[D];電子科技大學(xué);2009年

5 劉靜;機(jī)載環(huán)境下語(yǔ)音噪聲抑制技術(shù)研究及實(shí)現(xiàn)[D];電子科技大學(xué);2008年

6 鄧克巖;基于譜減法的語(yǔ)音增強(qiáng)在DSP環(huán)境下實(shí)時(shí)實(shí)現(xiàn)的研究[D];蘭州交通大學(xué);2006年

，

本文編號(hào)：2253868