基於支持向量機之語者驗證超大型積體電路架構設計; VLSI Architecture Design for SVM-Based Speaker Verification

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/61582

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/61582

題名:	基於支持向量機之語者驗證超大型積體電路架構設計;VLSI Architecture Design for SVM-Based Speaker Verification
作者:	連禮勳;Lian,Li-Xun
貢獻者:	資訊工程學系
關鍵詞:	語者驗證;超大型積體電路架構設計;支持向量機;高斯混合模型;超大型向量;座標旋轉運算器;speaker verification;VLSI;support vector machine(SVM);Gaussian mixture model(GMM);supervector;CORDIC
日期:	2013-08-26
上傳時間:	2013-10-08 15:22:55 (UTC+8)
出版者:	國立中央大學
摘要:	本篇論文提出了一種全新的VLSI架構來實現SVM與GMM-Supervector並可應用於語者驗證(Speaker Verification)或語者辨識(Speaker Identification) 。在SVM-Based的方法中，Decision Function為一不單是計算量相當龐大，還包括RBF核化函數裡面複雜的運算。且Decision Function需要與大量的支持向量(Support Vecotr)進行運算，如果我們想要達到Real-Time的效果以及不錯的辨識率對硬體設計而言則是相當的困難。因此我們提出了全新高斯核化單元(Gaussian Kernel Unit)，裡面包括數個可平行的Gaussian-PE。在每個Gaussian-PE中還包含了一個改良過CORDIC架構的指數單元(Exponential Unit)，改良過後的指數單元(Exponential Unit)可幫我們快速地來計算指數函數且較不佔面積，使得我們可平行化的數目增加。我們同樣的也完成了SVM-Based語者驗證之VLSI並且可支援相當多的支持向量個數，並且擁有不錯的運算速度。另外在GMM-Supervector的方法中，MAP的調適針對硬體而言已經是相當複雜的運算，並且大量的高斯個數更會對此方法如果有Real-Time的需求困難度大增。因此我們提出了全新的GMM-Supervector的硬體架構，包括我們在高斯混合模型模組(GMM Module)做了一些調整，可幫我們快速的運算GMM的值。並且我們提出全新的MAP模組，裡面包含數個平行的MAP-PE，每個MAP-PE接可快速地幫我們計算出調適後的高斯mean值，進而提升我們整體的系統速度，且我們的架構也可與我們提出的SVM-Based的硬體架構作結合，完成一全新的GMM-Supervector語者驗證之VLSI架構，並可達到不錯的辨識率及效率。 This paper presents a VLSI chip design for support vector machine (SVM) and GMM-Supervector (Gaussian Mixture Model-Supervector) based speaker verification. In SVM-Based method, the proposed chip consists mainly of a speaker feature extraction (SFE) module, an SVM module, and a decision module. The SFE module performs autocorrelation analysis, linear predictive coefficient (LPC) extraction, and LPC to cepstrum conversion. The SVM module includes a Gaussian kernel unit and a scaling unit. The purpose of Gaussian kernel unit is to evaluate the kernel value of a test vector and a support vector first. Four Gaussian kernel parallel processing elements (GK-PEs) are design to process four support vectors simultaneously. Each GK-PE is designed by a pipeline fashion and capable of perform 2-norm and exponential operations. An enhanced CORDIC architecture is presented to calculate the exponential value. In addition to the Gaussian kernel unit, a scaling unit is also developed in the SVM module. The scaling unit is used to perform scaling multiplications and complete the remaining operations of SVM decision value evaluation. Finally, the decision module accumulates the frame scores generated by all the test frames, and then compare it with a threshold to see if the test utterance is spoken by the claimed speaker. This chip design is characterized by its high speed, capable of handling a large number of support vectors in SVM. In GMM-Supervector method, the proposed chip consists mainly of a speaker feature extraction (SFE) module, a Gaussian mixture model (GMM) module, an MAP module, an SVM module. The GMM module can help us to compute the result of GMM quickly, and we propose a new MAP module, which contains numbers of parallel MAP-PE, each MAP-PE can help us calculate Gaussian mean values after adaptation quickly, thereby this paper enhance the speed of the overall system.
顯示於類別:	[資訊工程研究所] 博碩士論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	713	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....