近年來由於旅遊的盛行，國人出國觀光的人數年年呈現正成長，尤其是到離台灣最近的日本與韓國更是如此。根據中華民國交通部觀光局的統計，國人出國旅遊之地區人口數，日韓高居第三與第四名，僅次於中國大陸與香港。中華文化對日韓兩國的文字語言與風俗民情，一直保有深遠的影響。日本與韓國都曾使用漢字作為他們的古代文字。日本街頭的商業招牌，隨處可見漢字的蹤影。而韓語則有近七成以上的詞彙，其發音皆由古漢語字詞所組成。亞洲特有的漢字文化圈，便在中日韓三種語言的場域中形成。而國內亦受日韓文化的影響，從平面影視到生活喜好，從日韓戲劇到流行服飾，日流與韓流深受國人所喜愛。因此吾人希望建構一套日韓文字語音辨識系統，不僅提供國人語言學習與出外旅遊之用，更能進一步體驗兩國之文化，開闊吾人生活之視野。
本論文探討日文與韓文文字與語音辨識系統之設計與實作策略。就文字辨識部分，吾人首先將日文歸納出152類假名及2,427類常用漢字，韓文歸納出984類單字模型，其次以二維傅立葉轉換及卡式轉換進行特徵萃取，最後用餘弦相似法則與文字結構學，做字詞之決斷。在Intel Core i5時脈2.3 GHz個人電腦與Windows 7之作業系統環境下，針對5,000筆日文與5,000筆韓文字詞資料庫，吾人可分別獲得98.86% 與97.56% 之正確字詞辨識率。就語音辨識部分，吾人依據日韓語之發音特性，首先將日語歸納出207類單音與韓語712類單音，其次運用梅爾頻率倒頻譜係數及線性預估倒頻譜係數，進行單音節雙特徵參數萃取，最後以隱藏式馬可夫模型與音位結構學，做語詞之最終判定。在Intel Core2 Quad 時脈2.5 GHz之個人電腦與Ubuntu 12.04之作業系統環境下，針對4,485筆日語與 4,546筆韓語語詞資料庫，正確語詞辨識率可分別達到95.83% 與95.62%。

Traveling becomes more and more popular in the recent years. According to the statistics of Tourism Bureau, Ministry of Transportation and Communications, ROC, the number of tourists abroad grew at a steady pace during the past few years, especially in the neighboring Japan and Korea. The tourist population from Taiwan to Japan and Korea are ranked number three and number four, just fewer than that of Mainland China and Hong Kong. Chinese culture has been influencing language, custom and tradition for both countries since 200 B.C. Chinese characters were used as their ancient writing systems. Commercial signboards in Kanji can be found today all over the Japanese streets. And more than 70% of the Korean vocabularies can be pronounced from ancient Chinese. A unique Chinese cultural circle in Asia is forming under the realm of the three languages. In Taiwan, Japanese and Korean waves have significant impacts from the show business to the life styles of common people. Drama and fashion are the favorites. Hence, it is our objective to establish a character and speech recognition system for Japanese and Korean to learn the languages, to experience the cultures and to widen our perspectives as well.
In this thesis, a bilingual character and speech recognition system for Japanese and Korean is designed and implemented. Two-dimensional Fourier transform and Karhunen-Loeve transform are used to extract the character features of 152 Japanese Kana classes, 2,427 Japanese Kanji classes and 984 Korean syllable patterns. Cosine similarity of the features and literal structure of the two languages are then applied to find the final answer. Under the 2.3 GHz Intel Core i5 PC and Windows 7 operating system environment, correct character recognition rates of 98.86% and 97.56% can be reached respectively for the 5,000 Japanese word and 5,000 Korean word databases. Mel-frequency cepstral coefficients and linear predicted cepstral coefficients are utilized for the speech feature extraction of the selected 207 Japanese and 712 Korean common syllables. Hidden Markov model and phonotactics are then employed to obtain the ultimate solution. Under the 2.5 GHz Intel Core2 Quad PC and Ubuntu 12.04 operating system environment, correct speech recognition rates of 95.83% and 95.62% can be attained respectively for the 4,485 Japanese word and 4,546 Korean word databases.

論文審定書 i
誌謝 ii
摘要 iii
目錄 v
圖次 viii
表次 x
第一章 緒論 1
1-1研究動機 1
1-2研究目的與方法 2
1-3論文章節概要 2
第二章 語言學 3
2-1日文介紹 4
2-1-1日文文字與發音規則 4
2-1-2日文五十音 5
2-2韓文介紹 9
2-2-1韓文文字與發音規則 9
2-2-2韓文書寫方式 11
第三章 影像辨識系統理論 14
3-1影像辨識流程簡介 14
3-2影像前處理 15
3-2-1影像歪斜校正 16
3-2-1雜訊去除 19
3-2-2影像切割 21
3-3 影像特徵值萃取 22
3-3-1 頻域特徵 22
3-3-2 卡式轉換 29
3-4 餘弦相似度 31
3-5 文字結構學 32
第四章 語音辨識系統的流程與原理 33
4-1辨識系統架構流程 33
4-2-1 能量 34
4-2-2 越零率 34
4-3特徵萃取前處理 35
4-3-1 預強 35
4-3-2 加視窗 36
4-4特徵萃取流程 37
4-4-1梅爾頻率倒頻譜係數 37
4-4-2 線性預估倒頻譜係數 40
4-5 隱藏式馬可夫模型 43
4-5-1 估算狀態路徑機率 45
4-5-2 最佳狀態序列問題 47
4-5-3 模型參數估算問題 49
第五章 辨識系統訓練策略及效益 50
5-1 硬體設備與系統參數 50
5-2 文字模型建立與訓練 50
5-3 系統辨識效能 53
第六章 語音辨識系統訓練策略及效益 54
6-1 硬體設備與系統參數 54
6-2單音模型建立與訓練 55
6-3 系統辨識效能 56
第七章 結論與未來展望 58
參考文獻 59

[1] 中華民國交通部觀光局 http://admin.taiwan.net.tw/
[2] 維基百科，http://zh.wikipedia.org/
[3] 黃華章，華人的日語語音學，致良出版社，民國93年
[4] 簡江作，最新韓國語會話，國立編譯館，民國91年
[5] 鐘國亮，影像處理與電腦視覺，東華書局，民國101年
[6] 麥克安竹 (McAndrew, Alasdair)，數位影像處理，新加坡商聖智學習出版，民國99年
[7] K. Karhunen, Ueber lineare Methoden in der Wahrscheinlichkeitsrechnung, Ann. Ac. Sci. Fennicae, series A. I., 37, Mathematica-Physica, 1947
[8] G. Salton and M. J. McGill, Introduction to Modern Information Retrieval, McGraw-Hill, New York,1983
[9] 王小川，語音訊號處理，全華，民國93年
[10] Lawrence R. Rabiner and Ronald W. Schafer,Theory and Applications of Digital Speech Processing, Prentice Hall, Taiwan, 2010
[11] Chuan-Jie Lin and Hsin-His Chen, "A Mandarin to Taiwanese Min Nan Machine Translation System with Speech Synthesis of Taiwanese Min Nan", Computational Linguistics and Chinese Language Processing, 1999
[12] Wai C. Chu, Speech Coding Algorithms, Wiley Interscience, New Jersey, 2003
[13] Xuedong Huang, Alex Acero, and Hsiao-Wuen Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development, Pearson Education,Taiwan, 2005
[14] Daniel Jurafsky and James H. Martin, Speech and Language Processing, Prentice Hall, Taiwan, 2009