文本無關的多說話人確認研究
發(fā)布時間：2018-08-27 09:52
【摘要】：近年來,在生物特征識別領域,說話人識別以其獨特的安全性、經濟性和準確性等優(yōu)勢受到越來越多的關注,并逐漸成為人們生活和工作中重要的身份驗證方式,具有廣闊的市場前景。說話人識別的一個重要研究分支是說話人確認,本文著重對說話人確認展開研究。本文從說話人確認的系統框架入手,對系統的各部分予以詳細的介紹。隨后針對復雜條件下的說話人確認問題,重點研究了特征提取、說話人分割、模型建立等技術。本文的主要研究工作及創(chuàng)新點如下:1.構建基于GMM-UBM的說話人確認系統并將其作為本文的基線系統,研究分析了影響系統性能的相關因素,包括高斯混合度、訓練語音長度、得分規(guī)整技術,并通過實驗進行驗證。2.在特征提取方面,為了提升噪聲環(huán)境下說話人確認系統的性能,本文提出了一種具有較強噪聲魯棒性的多窗譜減MFCC特征。多窗譜減MFCC是在已有多窗譜MFCC(Multitaper MFCC)基礎上的改進,主要是將多窗譜估計技術與譜減法進行了結合。仿真結果表明,當測試語音中含有加性噪聲時,與多窗譜MFCC提取算法相比,采用多窗譜減MFCC的說話人確認系統性能在等錯誤率EER和最小檢測代價函數值minDCF兩項評測指標上都取得了較好的結果。3.在說話人分割方面,針對傳統基于BIC的說話人分割算法累積計算量大、冗余分割點過多,導致分割速度慢、分割準確度降低的問題,相關文獻采用了分治算法對其進行改進,雖然改進法能夠大幅提高分割速度,但準確度卻有所降低。為了達到分割速度與分割準確度同時提高的目的,本文首先在具體實現BIC說話人分割算法時提出了三步分割的策略,在此基礎上引入分治算法思想對其進行改進。實驗結果表明,改進后的分割算法在分割速度上有較大提高,準確度上也有一定提升。4.在模型建立方面,探索研究了i-vector說話人建模技術,重點研究了i-vector的提取過程,構建基于i-vector的說話人確認系統,并將其與基于GMM-UBM的說話人確認系統進行了對比分析。
[Abstract]:In recent years, in the field of biometrics, speaker recognition has attracted more and more attention because of its unique advantages of security, economy and accuracy, and has gradually become an important way of identity verification in people's lives and work. It has broad market prospects. This paper begins with the system framework of speaker verification, and then introduces each part of the system in detail. Then, aiming at the speaker verification under complex conditions, it focuses on feature extraction, speaker segmentation, model building and other technologies. The main research work and innovation of this paper are as follows: 1. Based on the GMM-UBM speaker verification system as the baseline system of this paper, the related factors affecting the performance of the system are studied and analyzed, including Gaussian mixture, training speech length, scoring regularization technology, and verified by experiments. 2. In feature extraction, in order to improve the performance of speaker verification system in noisy environment, this paper proposes a method to improve the performance of the system. A multi-window spectral subtraction MFCC feature with strong noise robustness is proposed. The multi-window spectral subtraction MFCC is an improvement on the existing multi-window spectral MFCC (Multitaper MFCC), which combines the multi-window spectral estimation technique with the spectral subtraction method. The simulation results show that when the test speech contains additive noise, it is better than the multi-window spectral MFCC extraction algorithm. The speaker verification system using multi-window spectral subtraction MFCC achieves good results in EER with equal error rate and minDCF with minimum detection cost function. In order to improve the segmentation speed and accuracy at the same time, this paper first proposes a three-step segmentation strategy to implement the BIC speaker segmentation algorithm. The experimental results show that the improved segmentation algorithm has a great improvement in segmentation speed and accuracy. 4. In the aspect of model building, I-vector speaker modeling technology is explored and studied, especially the extraction process of I-vector and the construction of I-vector based speaker. The speaker recognition system is analyzed and compared with the speaker verification system based on GMM-UBM.
【學位授予單位】：電子科技大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：TN912.34
[Abstract]:In recent years, in the field of biometrics, speaker recognition has attracted more and more attention because of its unique advantages of security, economy and accuracy, and has gradually become an important way of identity verification in people's lives and work. It has broad market prospects. This paper begins with the system framework of speaker verification, and then introduces each part of the system in detail. Then, aiming at the speaker verification under complex conditions, it focuses on feature extraction, speaker segmentation, model building and other technologies. The main research work and innovation of this paper are as follows: 1. Based on the GMM-UBM speaker verification system as the baseline system of this paper, the related factors affecting the performance of the system are studied and analyzed, including Gaussian mixture, training speech length, scoring regularization technology, and verified by experiments. 2. In feature extraction, in order to improve the performance of speaker verification system in noisy environment, this paper proposes a method to improve the performance of the system. A multi-window spectral subtraction MFCC feature with strong noise robustness is proposed. The multi-window spectral subtraction MFCC is an improvement on the existing multi-window spectral MFCC (Multitaper MFCC), which combines the multi-window spectral estimation technique with the spectral subtraction method. The simulation results show that when the test speech contains additive noise, it is better than the multi-window spectral MFCC extraction algorithm. The speaker verification system using multi-window spectral subtraction MFCC achieves good results in EER with equal error rate and minDCF with minimum detection cost function. In order to improve the segmentation speed and accuracy at the same time, this paper first proposes a three-step segmentation strategy to implement the BIC speaker segmentation algorithm. The experimental results show that the improved segmentation algorithm has a great improvement in segmentation speed and accuracy. 4. In the aspect of model building, I-vector speaker modeling technology is explored and studied, especially the extraction process of I-vector and the construction of I-vector based speaker. The speaker recognition system is analyzed and compared with the speaker verification system based on GMM-UBM.
【學位授予單位】：電子科技大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：TN912.34
【共引文獻】
相關期刊論文 前10條
1 賀前華;王志鋒;Alexander I Rudnicky;朱錚宇;李新超;;基于改進PNCC特征和兩步區(qū)分性訓練的錄音設備識別方法[J];電子學報;2014年01期
2 黃奮;馬皓;鄧菁;;說話人識別技術在社保系統中的遠程身份認證應用研究[J];電子技術與軟件工程;2014年02期
3 馬勇;鮑長春;;基于稀疏神經網絡的說話人分割[J];北京工業(yè)大學學報;2015年05期
4 李晉;郭武;戴禮榮;;聯合因子分析算法中基于信號子空間的空間變換方法[J];模式識別與人工智能;2013年08期
5 楊棟;周秀玲;郭平;;基于貝葉斯通用背景模型的圖像標注[J];自動化學報;2013年10期
6 祝太鋒;;基于動態(tài)反饋負載均衡算法的改進[J];湖南農機;2013年11期
7 駱啟帆;章堅武;吳震東;;一種基于MFCC與韻律特征的說話人確認方法[J];杭州電子科技大學學報;2013年05期
8 陳麗萍;王爾玉;戴禮榮;宋彥;;基于深層置信網絡的說話人信息提取方法[J];模式識別與人工智能;2013年12期
9 廖曉鋒;范修斌;姜青山;;基于協方差的高斯混合模型參數學習算法[J];計算機科學;2013年S2期
10 郭心語;何曉豐;宮學慶;張蓉;周傲英;;一種基于曝光量和點擊率的用戶組優(yōu)化策略[J];計算機研究與發(fā)展;2013年S1期
相關會議論文 前6條
1 駱啟帆;章堅武;吳震東;;一種基于MFCC與韻律特征的說話人確認方法[A];浙江省電子學會2013學術年會論文集[C];2013年
2 尹聰;白靜;龔[，
本文編號：2206917
本文鏈接：http://sikaile.net/kejilunwen/wltx/2206917.html
教材專著
