發(fā)布時(shí)間：2018-03-24 07:11

  本文選題：盲源分離　切入點(diǎn)：帶噪混疊語音　出處：《北京交通大學(xué)》2014年碩士論文

【摘要】：語音是人類傳播信息和交流的重要媒介,人們可以在多個(gè)講話者的環(huán)境中區(qū)分和獲取自己感興趣的語音信號(hào),這是人體內(nèi)部語音理解機(jī)理特有的一種能力。如何通過機(jī)器從混合的語音信號(hào)中分離出各個(gè)源信號(hào),成為語音信號(hào)處理領(lǐng)域的一個(gè)重要問題。盲源分離(Blind Source Separation,BSS)是混疊語音分離的主要方法之一。盲源分離是指在源信號(hào)及其混合方式均未知的情況下,僅根據(jù)觀測(cè)到的若干混合信號(hào)恢復(fù)源信號(hào)的過程。目前的盲源分離基本上都是在無噪環(huán)境中進(jìn)行的,但是實(shí)際環(huán)境中,語音信號(hào)不可避免的會(huì)受到各種噪聲的影響,因此研究帶噪混疊語音分離方法具有重要的理論價(jià)值和實(shí)際意義。 本文對(duì)帶噪混疊語音信號(hào)進(jìn)行研究,結(jié)合盲源分離技術(shù),提出了一種有效的解決帶噪混疊語音盲分離的方法。首先消除帶噪混疊語音信號(hào)中的噪聲,提高信號(hào)的信噪比,然后再將去噪處理后混疊語音信號(hào)進(jìn)行多個(gè)說話人的語音分離；主要在去噪部分和語音分離部分對(duì)算法進(jìn)行改進(jìn),論文的主要工作包括： 第一,在帶噪混疊語音信號(hào)的噪聲消除方面,提出了一種基于改進(jìn)噪聲估計(jì)和幅度補(bǔ)償?shù)母倪M(jìn)的譜減法,該方法在有效去除噪聲的同時(shí)能極大限度的避免源信號(hào)受到損傷,為后續(xù)進(jìn)行的混疊語音信號(hào)分離工作奠定基礎(chǔ),可以在很大程度上避免由于源信號(hào)受到損傷而影響分離效果。 第二,在多個(gè)說話人的語音分離方面,提出了結(jié)合牛頓下降法和優(yōu)化快速獨(dú)立分量分析算法(M-FastICA)的改進(jìn)算法,解決基于負(fù)熵的FastICA算法對(duì)隨機(jī)初始分離矩陣敏感并存在局部最大值的問題,算法在保證分離效果的同時(shí)減小了對(duì)初始值的敏感度、降低了算法的計(jì)算迭代次數(shù)；同時(shí)根據(jù)語音信號(hào)的分布特性優(yōu)化選取分離算法中的非線性函數(shù),以提高算法的精度。最后,可以對(duì)分離信號(hào)進(jìn)行再消噪處理,從而進(jìn)一步提升分離語音信號(hào)的質(zhì)量。 仿真實(shí)驗(yàn)表明,論文所提算法具有很好的分離效果。從相似系數(shù)矩陣和最小均方誤差兩個(gè)指標(biāo)來看,論文所提算法與原始的FastICA算法相比有著更加出色的分離性能,算法迭代次數(shù)也下降了60%,降低了算法的復(fù)雜度。
[Abstract]:Speech is an important medium for the dissemination of information and communication among human beings. People can distinguish and acquire voice signals of interest to themselves in the context of multiple speakers. This is a unique ability of the human body's internal speech understanding mechanism. How to separate each source signal from a mixed speech signal through a machine, Blind Source Separation (BSS) is one of the main methods of speech separation. Blind source separation (BSS) means that the source signal and its mixing mode are unknown. The current blind source separation is basically carried out in noise-free environment, but in the actual environment, the speech signal will inevitably be affected by various kinds of noise. Therefore, it is of great theoretical and practical significance to study the noisy aliasing speech separation method. In this paper, we study the noisy aliasing speech signal, combine the blind source separation technology, propose an effective method to solve the blind separation of the noisy aliasing speech. Firstly, the noise in the noisy aliasing speech signal is eliminated, and the signal-to-noise ratio of the signal to noise is improved. Then, the speech separation of multiple speakers is carried out after the process of denoising, and the algorithm is improved mainly in the part of denoising and the part of speech separation. The main work of this paper is as follows:. First, an improved spectral subtraction method based on improved noise estimation and amplitude compensation is proposed for noise cancellation of noisy aliasing speech signals. It can lay a foundation for the subsequent work on the separation of aliasing speech signals, and can largely avoid the influence of source signal damage on the separation effect. Secondly, in the aspect of speech separation of multiple speakers, an improved algorithm combining Newton descent method and optimized fast independent component analysis algorithm (M-FastICA) is proposed. To solve the problem that FastICA algorithm based on negative entropy is sensitive to the random initial separation matrix and has local maximum value, the algorithm not only ensures the separation effect, but also reduces the sensitivity to initial value and reduces the number of iterations. At the same time, according to the distribution characteristics of the speech signal, the nonlinear function of the separation algorithm can be optimized to improve the accuracy of the algorithm. Finally, the separation signal can be de-noised and the quality of the separated speech signal can be further improved. The simulation results show that the proposed algorithm has a good separation effect. From the similarity coefficient matrix and the minimum mean square error, the proposed algorithm has a better separation performance than the original FastICA algorithm. The number of iterations of the algorithm is also reduced by 60%, which reduces the complexity of the algorithm.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN912.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 劉琚,聶開寶,李道真,何振亞;基于遞歸神經(jīng)網(wǎng)絡(luò)的信息理論盲源分離準(zhǔn)則[J];電路與系統(tǒng)學(xué)報(bào);2001年01期

2 陳雪勤,趙鶴鳴,陳小平;基于計(jì)算聽覺場(chǎng)景分析的強(qiáng)噪聲背景下基音檢測(cè)方法[J];電路與系統(tǒng)學(xué)報(bào);2003年03期

3 丁志剛,朱孝龍,焦李成;基于獨(dú)立分量分析的DS-CDMA系統(tǒng)接收機(jī)[J];電子學(xué)報(bào);2000年S1期

4 劉琚,何振亞;盲源分離和盲反卷積[J];電子學(xué)報(bào);2002年04期

5 虞曉,胡光銳;基于統(tǒng)計(jì)估計(jì)的盲信號(hào)分離算法[J];上海交通大學(xué)學(xué)報(bào);1999年05期

6 陳華富,堯德中;獨(dú)立成份分析的梯度算法及應(yīng)用[J];信號(hào)處理;2001年06期

相關(guān)博士學(xué)位論文 前1條

1 劉建強(qiáng);非平穩(wěn)環(huán)境中的盲源分離算法研究[D];西安電子科技大學(xué);2009年

，

本文編號(hào)：1657248