應用投票演算法之語者確認系統研究

The Application of Voting to the Speaker Verification System

陳柏仁(Bo-ren Chen)

指導教授 ： 莊堯棠

國立中央大學/資訊電機學院/電機工程學系/碩士(2007年)

摘要

本論文使用一種新的分數計算方法—投票演算法(Voting)，藉由此方法應用於語者確認系統上，使得語者確認系統的效能得到提升。
本論文將投票演算法與分數正規化(Test Normalization)結合，提出了四種新的語者確認系統架構，其中以改善混合式語者確認系統可以達到最大改善。實驗結果顯示，系統性能可達最好的相等錯誤率及決策成本函數為9.28%和0.1132，比起傳統的語者確認系統的效能12.53%和0.1534，改善了3.25%和0.0402；比起分數正規化式語者確認系統的效能9.87%和0.1154，改善了0.59%和0.0022。
本論文利用新的分數計算方法Voting，所提出的語者確認系統架構可以輔助分數正規化式語者確認系統，提供語者資訊，使系統性能達到改善。

關鍵字

語者確認

並列摘要

This thesis uses a kind of new score computing –Voting, making use of it on the speaker verification system and the efficiency of speaker verification system is improved.
We combine Voting and Test normalization and four new kinds of speaker verification system are proposed, improved hybrid speaker verification system can reach the greatest improvement. The experimental result shows, improved hybrid speaker verification system compare with the traditional speaker verification system that EER can be up to 3.25% and DCF can be up to 0.0402 of the improvement. Improved hybrid speaker verification system compare with the test normalization speaker verification system that EER can be up to 0.59% and DCF can be up to 0.0022 of the improvement.
The new speaker verification system we propose may assist with test normalization speaker verification system. The new system can supply speaker information and improve the efficiency of speaker verification system.

並列關鍵字

speaker verification

參考文獻

[1] A. Martin, G. Doddington, T. Kamn, M. Ordowski, and M, Przybocki, “The DET curve in assessment of detection task performance,” in Proceedings of European Conference on Speech Communication and Technology, pp. 1895-1898, 1997.

[2] B. Narayanaswamy, R. Gangadharaiah, “Extracting Additional Information from Gaussian Mixture Model Probabilities for Improved Text-Independent Speaker Identification,” Acoustics, Speech, and Signal Processing, vol. 1, pp 621-624, 2005.

[3] C. Auckenthaler, Lloyd-Thomas, “Score Normalization for Text-independent Speaker Verification System,” Digital Signal Processing, vol. 10 No1-3, 2000.

[4] C. P. Chen and J. Bilmes, “MVA Processing of Speech Features”, Audio, Speech and Language Processing, vol. 15, pp257-270, 2007.

[5] D. A. Reynolds and R. C. Rose, “Robust Text-Independent Speaker Identification Using Gaussian Mixture Models,” IEEE Trans. Speech and Audio Processing, vol. 3, no. 1, pp. 72-83, January 1995.