臺灣博碩士論文加值系統

音準不準與節拍錯誤是二胡初學者最常遇到的問題。傳統的二胡學習方式是使用調音器與節拍器來改善這兩個問題。但是對於初學二胡的學習者而言，在沒有教師從旁協助時，通常沒辦法明確瞭解如何改善這些問題。因此，本研究開發了一套「智慧型個人化二胡音準及節拍學習系統」，期望它能幫助二胡學習者在沒有教師協助時能夠隨時隨地學習二胡的音準與節拍，同時給予專業的回饋。此系統具備音準練習與節拍練習的功能，除了會依MML（Music Macro Language）格式自動生成樂譜外，也能讓二胡學習者可以跟著樂譜演奏。在演奏結束後，會依照演奏情形給予學習者該次演奏的評分，並針對各種音高與節拍提供專家般的評語。系統也會記錄學習者每次的練習狀況，並依照學習者的學習情況給予適當的鼓勵及學習引導，達到智慧型及個人化的學習鷹架。系統開發完後，本研究分別對音準系統與節拍系統進行了可用性評估實驗，探討可用性的各構面平均數，以及練習時間與接觸二胡時間對可用性評估之影響。結果顯示，可用性各構面平均數皆大於4.6，表示此系統對於二胡學習者是可以接受的，且練習時間與接觸二胡時間愈長的學習者對於系統接受度會高於經驗較少的二胡學習者。

Pitch accuracy and beat errors are the most common problems encountered by beginner erhu players. The traditional way of learning the erhu involves using a tuner and a metronome to improve these two issues. However, for beginner erhu learners without the assistance of a teacher, it is often difficult to understand how to address these problems effectively. Therefore, this study has developed an "Intelligent Personalized Erhu Pitch and Beat Learning System" in the hope that it can help erhu learners learn pitch and beat anytime and anywhere without the presence of a teacher, while providing professional feedback. This system features pitch exercises and beat exercises. In addition to automatically generating sheet music in the MML (Music Macro Language) format, it allows erhu learners to play along with the sheet music. After each performance, the system provides learners with a score based on their performance and offers expert-like comments on various pitch and beat aspects. The system also keeps a record of learners' practice sessions and provides appropriate encouragement and guidance based on their learning progress, creating an intelligent and personalized learning scaffold. After the development of the system, this study conducted usability evaluation experiments on both the pitch system and the beat system to explore the average scores of different usability dimensions and the influence of practice time and exposure to the erhu on usability evaluation. The results showed that the average scores for all usability dimensions were above 4.6, indicating that the system is acceptable for erhu learners. Moreover, learners with longer practice time and exposure to the erhu showed higher acceptance of the system compared to those with less experience in erhu learning.

摘要 i
Abstract ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1. 研究背景 1
1.2. 研究動機與目的 2
1.3. 論文架構 3
第二章 文獻探討 4
2.1. 科技輔助音準學習 4
2.2. 科技輔助節拍學習 5
2.3. 智慧型個人化系統 7
第三章 音訊處理 8
3.1. 音訊輸入 8
3.2. 音訊前處理 9
3.2.1. 音框 9
3.2.2. 窗函數 10
3.3. 音高追蹤 11
3.3.1. 自相關函數分析 11
3.3.2. 平均幅度差函数分析 12
3.3.3. 傅立葉轉換 13
3.3.4. 諧波積頻譜 14
3.4. 音高比對 15
3.4.1. 音高簡介 15
3.4.2. 偵測項目 16
3.4.3. 比對標準 17
3.5. 節拍比對 17
3.5.1. 節拍簡介 17
3.5.2. 偵測項目 19
3.5.3. 比對標準 19
第四章 系統介紹 22
4.1. 開發軟體與工具介紹 22
4.1.1. Unity 22
4.1.2. C# 22
4.1.3. 平板 23
4.1.4. XCharts 23
4.2. 系統架構 24
4.3. 系統功能 24
4.3.1. 登入畫面 24
4.3.2. 關卡選擇畫面 26
4.3.3. 調音器 27
4.3.4. 練習模式 28
4.3.5. 樂譜產生 29
4.3.6. 演奏與分析 31
4.3.7. 歷史紀錄 35
4.3.8. 歷史分析 36
第五章 實驗結果與分析 40
5.1. 系統可用性評估 40
5.2. 實驗對象 40
5.3. 研究工具 41
5.4. 實驗流程 43
5.5. 資料收集與分析 44
第六章 結論與未來展望 49
6.1. 結論 49
6.2. 未來展望 49
參考文獻 50
附錄 53
附錄一 音準練習題目 53
附錄二 節拍練習題目 60
附錄三 音準各調對應評語 63
附錄四 知情同意書 75
附錄五 二胡系統操作學習單 76

[1]李艷，淺談二胡的歷史與發展趨勢，中國教育導刊，39-40， 2010。
[2]劉向陽、王清濤，二胡集體課授課系統與優化教學，佳木斯大學社會科學學報，138-139，2010。
[3]中華民國國樂學會，考級檢定，http://www.scm.org.tw/， 2019。
[4]G. H. Hwang, B. Chen, C. W. Sung, T. H. Kuo, “To Explore the Effect of Age on Cognitive Load When Using Social Websites to Conduct Flipped Classrooms on Musical Instrument Performance Teaching - Taking Amateur Erhu Learners as an Example,” Paper presented at the 23rd International Conference on Computers in Education (ICCE2015), Hangzhou, China, Nov 2015.
[5]彭秋汶、黃國豪、李琛瑜、陳年興、張偉倫、林則勳，應用穿戴式與體感技術研發二胡演奏姿勢矯正系統，發表於第二十三屆全球華人計算機教育應用大會(GCCCE2019) ，華中師範大學，武漢，中國大陸，計畫編號：MOST 106-2511-S-224-003-MY2，2019 年 5 月。
[6]陳昭名，遊戲輔助小提琴初學者音準練習系統，國立暨南國際大學碩士論文，南投縣，2016。
[7]F. Kikukawa, S. Ishihara, M. Soga, H. Taki, “Development of A Learning Environment for Playing Erhu by Diagnosis and Advice regarding Finger Position on Strings.” NIME 2013, pp. 271-276 (2013).
[8]F. Kikukawa, M. Soga, H. Taki, “Development of a gesture learning environment for novices' erhu bow strokes.” Procedia Comput. Sci. 35, 1323-1332 (2014).
[9]J. H. Fonteles and M. A. F. Rodrigues, "User experience in a Kinect-based conducting system for visualization of musical structure," Entertainment Computing, vol. 37, p. 100399, 2021.
[10]A. D. P. dos Santos, L. Loke, K. Yacef, and R. Martinez-Maldonado, "Enriching teachers' assessments of rhythmic Forró dance skills by modelling motion sensor data," International Journal of Human-Computer Studies, vol. 161, p. 102776, 2022.
[11]S. Takeshi, T. Misa, “Development of a forearm motion learning-assist system for playing the Japanese shamisen instrument. ” Entertainment Computing, 46, 100564, 2023.
[12]Z. Tong, “ Research on the Model of Music Sight-Singing Guidance System Based on Artificial Intelligence. ” Complexity, https://doi.org/10.1155/2021/3332216 (2021).
[13]賈志琳、李政軒，人工智慧的實踐：對話式日語學習智慧家教系統進行日語補救教學之研究，教育實踐與研究，33(2)，1-41，2020。
[14]張智星，音訊處理與辨識，http://mirlab.org/jang/books/audioSignalProcessing/，2009。
[15]M. R. Schroeder, “Period Histogram and Product Spectrum: New Methods for Fundamental Frequency Measurement,” Journal of the Acoustical Society of America, 43(4): 829-834, 1968.
[16]黃國豪、黃永廣、蔡秉宗，二胡音準輔助學習系統開發與成效評估，TANET2020，1457-1461，2020。
[17]A. J. Ellis, “On the sensations of tone as a physiological basis for the theory of music,” London: Longmans, Green and Company, 1875.
[18]P. Isabelle, K. L. Hyde, “What is specific to music processing? Insights from congenital amusia. ” Trends in cognitive sciences, 7(8), 362-367 (2003).
[19]董榕森，南胡教本第一冊臺北，樂韻出版社，2002。
[20]J. Nielsen, “Enhancing the explanatory power of usability heuristics,” Paper presented at the Human Factors Computing Systems, Boston, USA, 1994.
[21]J. Nielsen, “Heuristic evaluation,” Usability inspection methods, New York: John, 1994.
[22]R. Likert, “A technique for the measurement of attitudes,” Archives of Psychology, 22(140), 1-55, 1932.