本論文旨在研製一款陪伴型機器人，此機器人可以由語者辨認情緒或判斷是否為緊急狀態，並做出不同反應撫慰使用者的情緒或通知身旁人員協助使用者。
機器人內部支撐和手部構造由3D Printer列印，將微處理器、喇叭和馬達固定在機器人上。
機器人以dsPIC30F4011為控制晶片，驅動馬達控制手部動作和利用喇叭撥放不同音樂安慰使用者，並利用藍芽傳送結果給手機APP。
語音情緒辨識採用Hilbert Huang Transform (HHT)分解訊號，將訊號分解成不同的模態函數，利用頻率能量分類情緒，整體辨識率為93.75%。
機器人藉由語音辨識辨認使用者是否說出救命。語音辨識採用Mel-Frequency Cepstral Coefficients取出39階特徵，並利用Dynamic Time Warping (DTW)分類是否為緊急狀態，最終辨識率為87.9%。

This thesis develops a companion robot for recognizing the user’s emotion and judging whether the user is in the urgent situation or not. The robot can react to the user in different ways, and these reactions have a comforting effect. It also can give the alarm to the people who can help the user in danger.
The arm structure and supporting construction with microcontrollers, speaker and motors are developed by 3D-printing.
The brain of this robot is microcontroller dsPIC30F4011 which can drive motors to move the arm structure, control the speaker to play the healing music and finally send the results to mobile application by Bluetooth.
Hilbert Huang Transform(HHT) is adopted to process the voice signals. It can transform the single voice signal into the multiple sine waves which mean different frequencies. By the energy of these different frequencies, the robot recognizes the emotion successfully. The recognition rate is 87.9%.
If user asks for help, the robot raises the alarm. To judge the user’s situation, the speech recognition is used. The feature extraction technique of speech recognition is Mel-Frequency Cepstral Coefficients (MFCC). With 39 order MFCC features and Dynamic Time Warping(DTW), the robot can classify if the user is in danger or not. The recognition rate for speech recognition is 93.75%.

[1]R. Aminuddin, A. Sharkey and L. Levita, “Interaction with the Paro Robot May Reduce Psychophysiological Stress Responses,” 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 593-594, 2016
[2]W.-L. Chang, S. Šabanović and L. Huber, “Use of Seal-Like Robot PARO in Sensory Group Therapy for Older Adults with Dementia,” IEEE 13th International Conference on Rehabilitation Robotics (ICORR), pp. 101-102, 2013
[3]http://tpcjournal.taipower.com.tw/article/index/id/181, November, 2017
[4]http://technews.tw/2015/02/25/robear/, November, 2017
[5]C. Jayawardena, I.-H. Kuo, U. Unger, A. Igic, R. Wong, C. I. Watson, R. Q. Stafford, E. Broadbent, P. Tiwari, J. Warren, J. Sohn and B. A. MacDonald, “Deployment of a Service Robot to Help Older People,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5990-5995, 2010
[6]P. Benavidez, M. Kumar, S. Agaian and M. Jamshidi, “Design of a Home Multi-Robot System for the Elderly and Disabled,” 10th System of Systems Engineering Conference (SoSE), pp. 392-397, 2011
[7]J. Chan and G. Nejat,” A Learning-based Control Architecture for an Assistive Robot Providing Social Engagement during Cognitively Stimulating Activities,” IEEE International Conference on Robotics and Automation, pp. 3928-3933, 2011
[8]高于涵(2015)，友善的家庭陪伴型機器人。國立中央大學碩士論文。
[9]J. Woo, K. Wada and N. Kubota, “Robot Partner System for Elderly People Care by Using Sensor Network,” The Fourth IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics, pp. 1329-1334, 2012
[10]M. A. Anusuya and S. K. Katti, “Speech Recognition by Machine: A Review,” International Journal of Computer Science and Information Security (IJCSIS), pp. 181-205, 2009
[11]H. Gupta and D.N Gupta, “LPC and LPCC Method of Feature Extraction in Speech Recognition System,” IEEE 2016 6th International Conference - Cloud System and Big Data Engineering, pp. 498-502, 2016
[12]S. B. Davis and P. Mermelstein, “Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences,” IEEE Transactions on Acoustics, Speech, and Signal Processing, pp.357-366,1980
[13]N. S Nehe and R. S Holambe, “DWT and LPC Based Feature Extraction Methods for Isolated Word Recognition,” EURASIP Journal on Audio, Speech and Music Processing, 2012
[14]U. Shrawankar and V. Thakare, “Techniques for Feature Extraction in Speech Recognition System: A Comparative Study,” International Journal Of Computer Applications In Engineering, Technology and Sciences (IJCAETS), pp. 412-418, 2010
[15]P. Shen, C.-J.Zhou and X. Chen, “Automatic Speech Emotion Recognition Using Support Vector Machine,” Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology, pp. 621-625, 2011
[16]http://emodb.bilderbar.info/start.html, November, 2017
[17]https://www.csie.ntu.edu.tw/~cjlin/libsvm/, November, 2017
[18]A. Milton, S. S. Roy and S. T. Selvi, “SVM Scheme for Speech Emotion Recognition Using MFCC Feature,” International Journal of Computer Applications, pp. 34-39, 2013
[19]Shambhavi S. S and V. N Nitnaware, “Emotion Speech Recognition Using MFCC and SVM,” International Journal of Engineering Research & Technology, pp. 1067-1070, 2015
[20]W. Zhang, X.-Y. Zhang and Y. Sun, “Based on EEMD-HHT Marginal Spectrum of Speech Emotion Recognition,” 2012 International Conference on Computing, Measurement, Control and Sensor Network, pp. 91-94, 2012
[21]L. Xiang, W.-H. Xiong, J.-F. Li and R.-S. Ji, “Application of EEMD and Hilbert Marginal Spectrum in Speech Emotion Feature Extraction,” Control Conference, pp. 3686-3689, 2012
[22]Z.-L. Wang, H.-F. Li and L. Ma, “HHT Based Long Term Feature Extracting Method for Speech Emotion Classification,” Audio, Language and Image Processing, pp. 276-281, 2012
[23]http://ww1.microchip.com/downloads/en/devicedoc/70135C.pdf, November, 2017
[24]https://hobbytronics.com.pk/product/lm2596-adjustable-dc-dc-step-down-power-supply-module/, November, 2017
[25]http://goods.ruten.com.tw/item/show?21204135611196, November, 2017
[26]http://akizukidenshi.com/catalog/g/gI-02001/, November, 2017
[27]https://uge-one.com/pc817-optocoupler-optoisolator-dip-ic.html, November, 2017
[28]http://www.playrobot.com/storage/1758-micro-sd-tf-card-memory-shield-module-spi.html, November, 2017
[29]https://iamzxlee.wordpress.com/2014/07/20/lm386-low-voltage-audio-power-amplifier/, November, 2017
[30]https://lowvoltage.wordpress.com/tag/lm386/, November, 2017
[31]http://www.pmai.tn.edu.tw/df_ufiles/df_pics/32710%E7%AC%AC14%E7%AB%A0.pdf, November, 2017
[32]S. D. Dhingra, G. Nijhawan and P. Pandit, “Isolated Speech Recognition Using MFCC and DTW,” International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, pp. 4085-4092, 2013
[33]W. H. Abdulla, D. Chow and G. Sin, “Cross-Words Reference Tempiate for DTW Based Speech Recognition Systems,” TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region, pp. 1576-1579, 2003
[34]http://blog.csdn.net/zouxy09/article/details/9156785, November, 2017
[35]http://mirlab.org/jang/books/audiosignalprocessing/ptFreqDomainCepstrum.asp?title=7-8%20Cepstrum, November, 2017
[36]Y.-K. Lau and C.-K. Chan., “Speech Recognition Based on Zero Crossing Rate and Energy,” IEEE Transactions on Acoustics, Speech, and Signal Processing, pp. 320-323, 1985
[37]D. Jurafsky and J. H. Martin., “Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition,” ch.9 pp.1-72 ,2007
[38]陳松琳(2002)，以類神經網路為架構之語音辨識系統。國立中山大學碩士論文。
[39]http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/, November, 2017
[40]S. Salvador and P. Chan, “FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space,” KDD Workshop on Mining Temporal and Sequential Data, pp. 70-80, 2004
[41]M. Ayadi, M. S.Kamel and F. Karray, “Survey on Speech Emotion Recognition: Features, Classification Schemes, and Databases,” Pattern Recognition, pp. 572-587, 2010
[42]N. E. Huang and S P Shen(2014), “Hilbert-Huang Transform and Its Applications,” World Scientific Pub Co Inc
[43]楊佳穎(2008)，以HHT為基礎之肺音與哮喘音辨識研究。國立台北科技大學碩士論文。
[44]http://perso.ens-lyon.fr/patrick.flandrin/emd.html, November, 2017
[45]C.-D. Jiang, H.-W. Ko, C.-C. Wu, H.-C. Min, T.-J. Pyng, C.-W. Ling, “Applications of Hilbert-Huang Transform to Structural Damage Detection,” Structural Engineering and Mechanics, pp.1-20, 2011
[46]M.Kedadouche, M.Thomas and A.Tahan, “A Comparative Study between Empirical Wavelet Transforms and Empirical Mode Decomposition Methods: Application to Bearing Defect Diagnosis,” Mechanical Systems and Signal Processing, pp. 87-107, 2016