本文設計了以Microsoft Windows 作為作業平台之多國語言辨識系統。本系統採用語料之共振峰作為特徵並以向量量化方式淢少特徵量。在特徵粹取上,本文採用LPC求根之方法估測共振峰值,在比對方面,本文採用n-Gram碼及HMM模型作為比對方法。此外,本文亦提出一種新的距離量度應用於VQ上。

A Microsoft Windows program is designed to implement a Multi-Language Identification system based on formants estimation and vector quantization classifier with n-Gram and HMM. LPC is used here as an effective method for formants feature extraction of the speakers, and a new method for distance measure of VQ is also proposed.

目錄
頁次
論文摘要 II
致謝 III
主要圖表目錄 VI
第一章 緒論
1-1簡介(Introduction) 1
1-2 語言辨識系統介紹 2
1-3 論文主題 4
1-4 論文架構 5
第二章 語音訊號處理
2-1 短時域分析(Short Time Analysis) 6
2-2 預強(Pre-emphasis)與靜音切割 11
2-3 聲紋特徵(Formants) 15
2-4 利用倒頻譜(Cepstrum)作共振峰估測 16
2-5 利用線性預估編碼(LPC)作共振峰估測 19
第三章 語音編碼(Coding)
3-1 編碼(Coding)與分群(Cluster) 23
3-2 向量量化(Vector Quantization) 25
3-3 k-Means 28
3-4 Fuzzy k-Means 30
3-5 距離加權向量量化器 34
第四章 語言特徵與辨識
4-1 語言的特徵 42
4-2 n-Gram 44
4-3 Hidden Markov Model 45
4-4 應用 HMM 於 n-Gram 碼之比對 49
第五章 系統設計與實作
5-1 物件導向的系統規劃 50
5-2 系統規格 52
5-3 OGI-TS 資料庫 55
5-4 結果與未來展望 57

Reference:
[1] Marc A. Zissman, “Comparison of Four Approaches to Automatic Language Identification of Telephone Speech”, in IEEE Transactions On Speech and Audio Processing. Vol. 4, NO. 1, January 1996

[2] Alan V.Oppenheim, Ronald W.Schafer, “Discrete-Time Signal Processing” Prentice Hall.

[3] J. T. Foil, “Language identification using noisy speech,” in Proc. ICASSP ’86, vol. 2, Apr. 1986, pp. 861-864.

[4] M. Sugiyama, “Automatic language recognition using acoustic features,” in Proc. ICASSP ’91, vol. 2, May 1991, pp.831-816.

[5] R. B. Ives, “A minimal rule AI expert system for real-time classification of natural spoken languages,” in Proc. Second Ann. Artifical Intell. Adv. Comput. Technol. Conf., Long Beach, CA, May 1986, pp. 337-340.

[6] Y. K. Muthusamy and R. A. Cole, “Automatic segmentation and identification of ten languages using telephone speech,” in Proc. ICSLP ’92, vol. 2, Oct. 1992, pp.1007-1010

[7] John, R.Deller, John G.Proaskis, John H.L.Hansen, “Discrete-time processing of speech signals”.

[8] R. M. Gray, A.Buzo, A.H. Gray, Jr., and Y. Matsuyama, “Distortion measures for speech processing,” IEEE Trans. Acoustics, Speech, Signal Proc., ASSP-28 (4): 367-376, August 1980.

[9] 劉振源, “類神經網路模型與語音辨識”, 全華出版社

[10] Y. K. Muthusamy, E. Barnard, and R. A. Cole, “Reviewing automatic language identification,” IEEE Signal Processing Mag., vol. 11, no. 4, pp. 33-41, Oct. 1994

[11] Lutz Welling, Hermann Ney, “Formant Estimation for Speech Recognition”, IEEE Transactions on Speech and Audio Processing, VOL. 6, NO. 1, January 1998, pp. 36-48.

[12] 林壽, 王理嘉, “語音學教程”, 五南圖書出版公司

[13] Deller, Proakis, Hansen, “Discrete-Time Processing of Speech Signals” p. 105.

[14]E. R. Ruspini, “A new approach to clustering,” Inform. Contr., vol. 19, pp.22-32, 1969.

[15]J. C. Bezdek, “A convergence theorem for the fuzzy IDODATA clustering algorithms, “IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 1-8, Jan. 1980.