發(fā)布時間：2018-04-08 14:47

  本文選題：聲源辨別　切入點：聲音信號分離　出處：《江蘇科技大學》2017年碩士論文

【摘要】：人們聽到的聲音往往都是由多個聲音混合而成的,如何從混合的聲音信號中快速而準確的分辨出感興趣的聲音信號,一直是研究的熱點。傳統(tǒng)的方法可以進行簡單的聲源辨別,但是當涉及到大數(shù)據(jù)量的聲音信號處理時,影響了其應用的實時性和準確性。隨著人工智能時代的到來,以深度學習和GPU并行計算為代表的新技術(shù)為大數(shù)據(jù)量的聲音信號處理提供了解決思路,為此本文設(shè)計了混合聲音信號辨別的并行化方法,并開展了以下工作:1.分析了國內(nèi)外混合聲音信號的研究現(xiàn)狀以及發(fā)展趨勢,以混合聲音信號為切入點,學習了混合聲音信號辨別和GPU并行計算的相關(guān)知識,并研究了混合聲音信號分離以及聲源辨別的常用方法。2.對混合聲音信號進行去均值和白化等預處理,選取基于負熵的Fast-ICA算法進行混合聲音信號分離,通過分析混合聲音信號分離過程尋找制約其快速分離的原因,并利用GPU并行化進行加速改進。3.對分離后的聲音信號進行多特征值提取,并將提取出的特征值進行融合組成復合特征值,再進行聲源辨別。在辨別過程中,由于傳統(tǒng)神經(jīng)網(wǎng)絡(luò)存在學習能力不足的問題,針對這個缺陷,引入了基于深度信念網(wǎng)絡(luò)(DBN)的聲源辨別模型,以提升混合聲音信號辨別的準確率。4.由于要進行大數(shù)據(jù)量的聲音信號處理,并且聲音信號在處理過程中同時又具有方法一致、獨立性強的特點,于是采用GPU并行化方法分別對基于負熵的Fast ICA算法、特征值提取和深度信念網(wǎng)絡(luò)模型的訓練過程等操作進行優(yōu)化,提高了混合聲音信號辨別方法的處理效率。通過仿真和實驗驗證,利用GPU并行化對混合聲音信號的辨別方法進行優(yōu)化改進,提高了混合聲音信號分離和辨別的效率,滿足了實時性要求。同時,采用基于多特征值融合的復合特征值作為輸入數(shù)據(jù)和基于深度信念網(wǎng)絡(luò)的聲源辨別模型,提升了混合聲音信號辨別的準確率。
[Abstract]:The sound that people hear is often composed of multiple sounds. How to quickly and accurately distinguish the interesting sound signal from the mixed sound signal has always been a hot research topic.The traditional method can distinguish the sound source easily, but it affects the real time and the accuracy of the application when dealing with the sound signal processing of the large amount of data.With the arrival of the era of artificial intelligence, the new technology, represented by deep learning and GPU parallel computing, provides a solution for the sound signal processing of large amount of data. In this paper, a parallelization method for the discrimination of mixed sound signals is designed.And carried out the following work: 1.This paper analyzes the research status and development trend of mixed sound signal at home and abroad. Taking mixed sound signal as the starting point, we study the related knowledge of mixed sound signal discrimination and GPU parallel computing.The common methods of mixed sound signal separation and sound source discrimination. 2.The mixed sound signal is pretreated with de-mean and whitening, and the Fast-ICA algorithm based on negative entropy is selected to separate the mixed sound signal. The reason for the fast separation of mixed sound signal is found by analyzing the separation process of mixed sound signal.And using GPU parallelization to accelerate the improvement. 3.The separated sound signal is extracted with multiple eigenvalues, and the extracted eigenvalues are fused to form composite eigenvalues, and then sound source identification is carried out.Due to the deficiency of learning ability in traditional neural networks, a sound source discrimination model based on deep belief network (DBN) is introduced to improve the accuracy of mixed sound signal discrimination.The extraction of eigenvalues and the training process of the depth belief network model are optimized to improve the processing efficiency of the mixed sound signal identification method.Through simulation and experimental verification, the GPU parallelization is used to optimize and improve the discrimination method of mixed sound signals, which improves the efficiency of separation and discrimination of mixed sound signals and meets the real-time requirements.At the same time, the composite eigenvalue based on multi-eigenvalue fusion is used as input data and the sound source discrimination model based on deep belief network is used to improve the accuracy of mixed sound signal identification.
【學位授予單位】：江蘇科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TN912.3

【參考文獻】

相關(guān)期刊論文 前8條

1 張春霞;姬楠楠;王冠偉;;受限波爾茲曼機[J];工程數(shù)學學報;2015年02期

2 張鳳儀;夏秀渝;冉國敬;何禮;葉于林;;多聲源環(huán)境下的魯棒說話人識別[J];計算機系統(tǒng)應用;2015年04期

3 駱巖紅;萬國峰;王建華;;基于CUDA架構(gòu)的FFT并行計算研究[J];自動化與儀器儀表;2014年12期

4 楊柳;劉鐵英;;CPU浮點運算和GPU的通用計算的技術(shù)差異[J];中國外資;2013年24期

5 劉雅琴;智愛娟;;幾種語音識別特征參數(shù)的研究[J];計算機技術(shù)與發(fā)展;2009年12期

6 左顥睿;張啟衡;徐勇;趙汝進;;基于GPU的并行優(yōu)化技術(shù)[J];計算機應用研究;2009年11期

7 張偉偉;楊鼎才;;用于說話人識別的MFCC的改進算法[J];電子測量技術(shù);2009年08期

8 ;Natural gradient-based recursive least-squares algorithm for adaptive blind source separation[J];Science in China(Series F:Information Sciences);2004年01期

相關(guān)會議論文 前1條

1 彭詩雅;;聲紋識別技術(shù)研究[A];第十六屆全國青年通信學術(shù)會議論文集（上）[C];2011年

相關(guān)碩士學位論文 前3條

1 呂超;聲源辨別及定位的并行化方法的研究與實現(xiàn)[D];江蘇科技大學;2016年

2 陸軍建;基于CUDA和深度置信網(wǎng)絡(luò)的手寫字符處理應用[D];華東理工大學;2015年

3 王櫻;基于CUDA的FFT并行計算研究[D];湖南大學;2012年

，

本文編號：1722077