臺灣博碩士論文加值系統

基於市面上所流通的語音辨識系統，皆開發給正常人顏面族群使用，而現今社會中還是有存在少數的語言障礙族群，其市面上所設計的語音辨識系統並沒有考量到顏面神經失調的患者，因此，對語言障礙族群來說相當不便。對此本研究提供一個友善的語音辨識系統，能夠針對患有非正常人顏面神經失調的特定使用者進行訓練調整，以達到符合自身的語音辨識系統。
在研究方法中，分別同時擷取特徵值、語音檔和臉部視訊圖像，設計「動態時間校正(Dynamic Time Warping, DTW)樣本比對」和「卷積神經網路(Convolutional Neural Network, CNN)深度學習」兩種不同的計算方法進行探討，此研究應用可以提供給非正常人顏面族群及照護師一個客觀參考的數據，本論文運用前述的方法發展非正常人顏面族群的「顏面程度檢測」和「單字發音辨識」等兩種照護應用。
動態時間校正樣本比對方法主要是藉由三維影像感測器擷取的臉部原始骨架座標，將臉部座標轉換設計成特徵值。特徵值是由「距離」和「面積」兩種類型特徵所設計，在這兩種類型特徵中各設計10維特徵值，總合設計20維特徵值。將所設計的特徵值運用動態時間校正進行資料比對，透過比對來檢測非正常人顏面程度及單字發音辨識，並且，在此部分研究中，動態時間校正比對所計算出的樣本差異距離值可提供作為設計非正常人顏面程度分級的重要參數。
卷積神經網路深度學習方法則是使用VGG架構中最多層的VGG19，整個網路的架構包含16層卷積層、5層池化層及3層全連結層。深度學習是藉由感測器擷取臉部固定位置的視訊及語音圖像，利用視訊及語音圖像運用VGG19架構進行顏面程度檢測及單字發音辨識，在卷積神經網路中設計四種不同的資料庫進行單模式資料CNN性能辨識及前述不同單模式CNN之資料融合評估。
在本論文的實驗中，本研究將非正常人顏面族群分為「左臉」及「右臉」辨識性能的計算，同時，由於本研究設計為單一個人專屬的照護系統，而最後的平均辨識性能是10位不同使用者的平均辨識結果。在運用動態時間校正進行本論文所設計20維影像感測特徵值的研究方面，「左臉」及「右臉」非正常人顏面程度的平均辨識性能分別為84.49%和84.44%，「左臉」及「右臉」非正常人單字發音的平均辨識性能分別為83.38%和82.77%；在卷積神經網路實驗中，本論文利用視訊及語音圖像分別設計四種不同的單模式資料庫進行CNN的性能評估，其中，在顏面程度檢測和單字發音辨識，利用視訊圖像模式資料皆達到性能最佳，「左臉」及「右臉」的非正常人顏面程度平均辨識性能分別為99.14%和98.59%，另外，「左臉」及「右臉」非正常人單字發音的平均辨識性能分別為95.25%和92.36%。

Generally, matured speech recognition technology has been successfully accepted by the person with all normal face conditions. However, this voice recognition system designed on the market nowadays does not consider patients with facial nerve disorders (i.e. abnormal faces). Therefore, general speech recognition will be quite inconvenient for such weak group. This thesis develops a friendly voice recognition system that can be properly tailored to specific users with abnormal faces of facial nerve disorders.
The developed system in this thesis will simultaneously capture voice and facial features. Two differently recognition approaches, dynamic time warping (DTW) and convolutional neural network (CNN), are used for recognition determinations in the system. The designed system in this thesis will provide objective references or suggestive information for the abnormal face group and also the professional caregiver. This paper uses the above-mentioned method to construct a practical application system to the abnormal face group. The constructed system can be realized in two types of care applications, rehabilitation degree detection and single-word (syllable in Mandarin) recognition.
The DTW method in this thesis mainly uses the designed 20-dimentinoal face features, converting the original space coordinates of the face captured by the three-dimensional image sensor to the feature values. The designed 20-dimentinoal face features mainly contains two different types, which are ‘distance’ and ‘area’ classes. For each type of features, 10-dimensional parameters are designed, i.e. 10-dimensional distance and 10-dimensinal area feature parameters. DTW with the designed face features are applied to two works of degree detection of abnormal faces and word recognition. In this part of the study, the calculated distortion distance of template matching can be provided as an important parameter in the work of degree detection of abnormal faces.
The CNN deep learning method uses the layered VGG19 contained in the VGG architecture. The entire network architecture of VGG19 contains 19 layers including 16 convolutional layers with pooling calculations and 3 fully connected layers. In the CNN method, the video and voice data of the person with abnormal faces is captured first by the sensor, and the VGG19 model is then used to determine the abnormal degree of the face and the pronunciation result of the single-word made by the abnormal. Four different databases, face RGB images denoting the abnormal face, face RGB images denoting the made single-word, speech spectrm images denoting the abnormal face, and speech spectrm images denoting the made single-word, are designed for performance evaluations of the CNN model.
In the experiment, persons with the abnormal face are divided into two different parts, left-side abnormal faces and right-side abnormal faces. The deisgned system in this thesis is used for single-person care applications, and recognition performances of CNN denote the averaged recongiton result of 10 different users. In the DTW method with the designed 20-dimentinoal face features, recognition works of abnormal face degrees have accuracy of 84.49% (left-side abnormal faces) and 84.44% (right-side abnormal faces); recognition works of single-word pronunciation have accuracy of 83.38% (left-side abnormal faces) and 82.77% (right-side abnormal faces). On the other hand, in the CNN deep learning method, face RGB data outperforms speech spectrum data in both of two recognition works. recognition works of abnormal face degrees have accuracy of 99.14% (left-side abnormal faces) and 98.59% (right-side abnormal faces); recognition works of single-word pronunciation have accuracy of 95.25% (left-side abnormal faces) and 92.36% (right-side abnormal faces).

摘要.....i
Abstract.....iii
誌謝.....v
目錄.....vi
表目錄.....viii
圖目錄.....xi
第一章 緒論.....1
1.1 研究動機.....1
1.2 文獻回顧與探討.....2
1.3 研究方向.....3
1.4 章節概要.....3
第二章 背景技術介紹.....4
2.1 KINECT SDK人臉三維擷取.....4
2.2 KINECT臉部資料擷取流程.....7
2.3 語音識別系統設計.....9
2.3.1 線性預測編碼的特徵擷取.....9
2.4 動態時間校正(Dynamic Time Warping, DTW).....11
2.4.1 附近路徑限制.....12
2.4.2 完整比對.....13
2.5 卷積神經網路(Convolutional Neural Network, CNN).....14
2.5.1 卷積層(Convolution Layer).....15
2.5.2 池化層(Pooling Layer).....17
2.5.3 全連結層(Fully Connected layer).....18
2.5.4 過度擬合(Dropout).....18
2.5.5 激勵函數(Excitation Function).....19
2.5.6 損失函數(Loss Function).....20
第三章 基於視訊及音訊感測之非正常人顏面族群的發音照護系統.....21
3.1 動態時間校正樣本比對辨識方法設計.....22
3.1.1 三維影像感測於臉部定位.....23
3.1.2 臉部部位原始特徵點.....23
3.1.3 臉部部位特徵點重心計算.....26
3.1.4 臉部部位相對距離及面積特徵值計算.....27
3.1.5 具臉部特徵設計的動態時間校正方法.....33
3.1.6 臉部特徵參數設計總結.....34
3.1.7 語音特徵擷取.....34
3.1.8 動態時間校正模型建立與辨識方法.....35
3.1.9 樣本比對之照護系統設計.....38
3.2 卷積神經網路深度學習辨識方法設計.....41
3.2.1 三維影像感測器擷取之臉部視訊圖像.....42
3.2.2 卷積神經網路(VGGNet模型).....45
3.2.3 VGG19模型分解圖.....46
3.2.4 深度學習之資料庫系統建置.....48
3.2.5 VGG16模型辨識評估比較.....49
3.2.6 資料融合評估.....50
3.2.7 視訊圖像之深度學習實際系統應用.....51
第四章 實驗結果與分析比較.....52
4.1 發音照護系統應用情境設定.....52
4.2 樣本比對辨識實驗.....55
4.2.1 樣本比對辨識實驗之實驗設定及資料庫建置.....56
4.2.2 樣本比對實驗結果.....58
4.2.3 樣本比對之發音照護辨識實驗結果.....79
4.3 深度學習辨識實驗.....82
4.3.1 深度學習辨識實驗之實驗設定及資料庫建置.....83
4.3.2 深度學習照護系統實驗限制.....87
4.3.3 深度學習實驗結果.....88
4.3.4 深度學習資料融合評估.....118
第五章 結論.....121
參考文獻.....122
附錄.....128
Extended Abstract.....219

[1]K. Murakami, T. Shibano, Y. Fujimoto and T. Yamaguchi, “Information Recommendation System for the Care Prevention Using a Communication Robot,” Proceedings of the SICE Annual Conference, Taipei, pp. 388-389, 2010.
[2]M. Ding, R. Ikeura, Y. Mori, T. Mukai and S. Hosoe, “Measurement of Human Body Stiffness for Lifting-Up Motion Generation Using Nursing-Care Assistant Robot — RIBA,” Proceedings of the IEEE Sensors, Baltimore, MD, pp. 1-4, 2013.
[3]H. S. Ahn, M. H. Lee, E. Broadbent and B. A. MacDonald, “Gathering Healthcare Service Robot Requirements from Young People’s Perceptions of an Older Care Robot,” Proceedings of the First IEEE International Conference on Robotic Computing (IRC), Taichung, pp. 22-27, 2017.
[4]H. Lee, S. Kim, J. Kim, J. Lee, A. Byun, H. Ryu and H. J. Kong, “Assessment of User Needs for the Teleconsultation Robot and the Bedside Robot Using Simulation,” Proceedings of the International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), Okinawa, pp. 126-128, 2017.
[5]S. Sempena, Nur Ulfa Maulidevi and Peb Ruswono Aryan, “Human Action Recognition Using Dynamic Time Warping,” Proceedings of the International Conference on Electrical Engineering and Informatics, Bandung, pp. 1-5, 2011.
[6]Y. Chen, Q. Wu and X. He, “Using Dynamic Programming to Match Human Behavior Sequences,” Proceedings of the 10th International Conference on Control, Automation, Robotics and Vision, Hanoi, pp. 1498-1503, 2008.
[7]B. Bhanu and Xiaoli Zhou, “Face Recognition from Face Profile Using Dynamic Time Warping,” Proceedings of the 17th International Conference on Pattern Recognition (ICPR), Cambridge, vol.4, pp. 499-502, 2004.
[8]F. Dornaika and F. Davoine, “View and Texture-Independent Facial Expression Recognition in Videos Using Dynamic Programming,” Proceedings of the IEEE International Conference on Image Processing, Genova, pp. II-1314, 2005.
[9]A. Brahme and U. Bhadade, “Marathi Digit Recognition Using Lip Geometric Shape Features and Dynamic Time Warping,” Proceedings of the TENCON 2017 - IEEE Region 10 Conference, Penang, pp. 974-979, 2017.
[10]G. García-Bautista, F. Trujillo-Romero and S. O. Caballero-Morales, “Mexican Sign Language Recognition Using Kinect and Data Time Warping Algorithm,” Proceedings of the International Conference on Electronics, Communications and Computers (CONIELECOMP), Cholula, pp. 1-5, 2017.
[11]G. Plouffe and A. Cretu, “Static and Dynamic Hand Gesture Recognition in Depth Data Using Dynamic Time Warping,” Proceedings of the IEEE Transactions on Instrumentation and Measurement, vol. 65, no. 2, pp. 305-316, Feb. 2016.
[12]L. Patras, I. Giosan and S. Nedevschi, “Body Gesture Validation Using Multi-Dimensional Dynamic Time Warping on Kinect Data,” Proceedings of the IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, pp. 301-307, 2015.
[13]S. Riofrío, D. Pozo, J. Rosero and J. Vásquez, “Gesture Recognition Using Dynamic Time Warping and Kinect: A Practical Approach,” Proceedings of the International Conference on Information Systems and Computer Science (INCISCOS), Quito, pp. 302-308, 2017.
[14]M. Salagar, P. Kulkarni and S. Gondane, “Implementation of Dynamic Time Warping for Gesture Recognition in Sign Language Using High Performance Computing,” Proceedings of the International Conference on Human Computer Interactions (ICHCI), Chennai, pp. 1-6, 2013.
[15]S. Giraldo, A. Ortega, A. Perez, R. Ramirez, G. Waddell and A. Williamon, “Automatic Assessment of Violin Performance Using Dynamic Time Warping Classification,” Proceedings of the 26th Signal Processing and Communications Applications Conference (SIU), Izmir, pp. 1-3, 2018.
[16]B. Huang and W. Kinsner, “ECG Frame Classification Using Dynamic Time Warping,” Proceedings of the IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373), Winnipeg, Manitoba, Canada, vol.2, pp. 1105-1110, 2002.
[17]S. Tsevas and D. K. Iakovidis, “Dynamic Time Warping Fusion for the Retrieval of Similar Patient Cases Represented by Multimodal Time-Series Medical Data,” Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine, Corfu, pp. 1-4, 2010.
[18]T. Nishino, Y. Kajikawa and M. Muneyasu, “Multimodal Person Authentication System Using Features of Utterance,” Proceedings of the International Symposium on Intelligent Signal Processing and Communications Systems, Taipei, pp. 43-47, 2012.
[19]D. K. Vishwakarma and S. Ansari, “A Framework for Human-Computer Interaction Using Dynamic Time Warping and Neural Network,” Proceedings of the International Conference on Inventive Computing and Informatics (ICICI), Coimbatore, pp. 242-246, 2017.
[20]C. Khorinphan and S. Saiyod, “Tone Detection of Thai Phonemes for Home Robot Based on Fundamental Frequency Analysis with Dynamic Time Warping,” Proceedings of the 5th International Conference on Business and Industrial Research (ICBIR), Bangkok, pp. 167-171, 2018.
[21]Che Yong Yeo, S. A. R. Al-Haddad and C. K. Ng, “Animal Voice Recognition for Identification (ID) Detection System,” Proceedings of the IEEE 7th International Colloquium on Signal Processing and its Applications, Penang, pp. 198-201, 2011.
[22]D. A. A. Tuasikal, H. Fakhrurroja and C. Machbub, “Voice Activation Using Speaker Recognition for Controlling Humanoid Robot,” Proceedings of the 2018 IEEE 8th International Conference on System Engineering and Technology (ICSET), Bandung, pp. 79-84, 2018.
[23]T. Dutta, “Dynamic Time Warping Based Approach to Text-Dependent Speaker Identification Using Spectrograms,” Proceedings of the Congress on Image and Signal Processing, Sanya, Hainan, pp. 354-360, 2008.
[24]B. M. Eskofier, S. I. Lee, J. F. Daneault, F. N. Golabchi, G. F. Carvalho, G. V. Diaz, S. Sapienza, G. Costante, J. Klucken, T. Kautz and P. Bonato, “Recent Machine Learning Advancements in Sensor-Based Mobility Analysis: Deep Learning for Parkinson's Disease Assessment,” Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, pp. 655-658, 2016.
[25]Z. Guo, M. Shen, L. Duan, Y. Zhou, J. Xiang, H. Ding, S. Chen, O. Deussen and G. Dan, “Deep Assessment Process: Objective Assessment Process for Unilateral Peripheral Dacial Paralysis Via Deep Convolutional Neural Network,” Proceedings of the IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, VIC, pp. 135-138, 2017.
[26]M. A. Haque, R. B. Batista, F. Noroozi, K. Kulkarni, C. B. Laursen, R. lrani, M. Bellantonio, S. Escalera, G. Anbarjafari, K. Nasrollahi, O. K. Andersen, E. G. Spaich and T. B. Moeslund, “Deep Multimodal Pain Recognition: A Database and Comparison of Spatio-Temporal Visual Modalities,” Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), Xi'an, pp. 250-257, 2018.
[27]S. Kumar, S. Conjeti, A. G. Roy, C. Wachinger and N. Navab, “InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation,” Proceedings of the IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, pp. 145-148, 2018.
[28]A. Antoniades, L. Spyrou, D. M. Lopez, A. Valentin, G. Alarcon, S. Sanei and C. C. Took, “Detection of Interictal Discharges with Convolutional Neural Networks Using Discrete Ordered Multichannel Intracranial EEG,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 25, no. 12, pp. 2285-2294, Dec. 2017.
[29]X. Zhang, W. Pan and P. Xiao, “In-Vivo Skin Capacitive Image Classification Using AlexNet Convolution Neural Network,” Proceedings of the IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, pp. 439-443, 2018.
[30]S. Roy, J. A. Butman, L. Chan and D. L. Pham, “TBI Contusion Segmentation from MRI Using Convolutional Neural Networks,” Proceedings of the IEEE 15th International Symposium on Biomedical Imaging (ISBI), Washington, DC, pp. 158-162, 2018.
[31]L. B. Maia, A. Lima, R. M. Pinheiro Pereira, G. B. Junior, J. Dallyson Sousa de Almeida and A. C. de Paiva, “Evaluation of Melanoma Diagnosis Using Deep Features,” Proceedings of the 25th International Conference on Systems, Signals and Image Processing (IWSSIP), Maribor, pp. 1-4, 2018.
[32]D. Ahmedt-Aristizabal, K. Nguyen, S. Denman, S. Sridharan, S. Dionisio and C. Fookes, “Deep Motion Analysis for Epileptic Seizure Classification,” Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, pp. 3578-3581, 2018.
[33]N. Churamani, P. Barros, E. Strahl and S. Wermter, “Learning Empathy-Driven Emotion Expressions Using Affective Modulations,” Proceedings of the International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, pp. 1-8, 2018.
[34]D. O. Pop, A. Rogozan, F. Nashashibi and A. Bensrhair, “Pedestrian Recognition Through Different Cross-Modality Deep Learning Methods,” Proceedings of the IEEE International Conference on Vehicular Electronics and Safety (ICVES), Vienna, pp. 133-138, 2017.
[35]H. El-Ghaish, M. E. Hussein, A. Shoukry and R. Onai, “Human Action Recognition Based on Integrating Body Pose, Part Shape, and Motion,” IEEE Access, vol. 6, pp. 49040-49055, 2018.
[36]S. Katakis, N. Barotsis, D. Kastaniotis, C. Theoharatos, D. Tsourounis, S. Fotopoulos and E. Panagiotopoulos, “Muscle Type Classification on Ultrasound Imaging Using Deep Convolutional Neural Networks,” Proceedings of the IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), Zagorochoria, pp. 1-5, 2018.
[37]A. Rueda and S. Krishnan, “Augmenting Dysphonia Voice Using Fourier-based Synchrosqueezing Transform for a CNN Classifier,” Proceedings of the ICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, pp. 6415-6419, 2019.
[38]H. Liang, X. Lin, Q. Zhang and X. Kang, “Recognition of Spoofed Voice Using Convolutional Neural Networks,” Proceedings of the IEEE Global Conference on Signal and Information Processing (GlobalSIP), Montreal, QC, pp. 293-297, 2017.
[39]H. Huang, W. Chen, C. Liu and S. D. You, “Singing Voice Detection Based on Convolutional Neural Networks,” Proceedings of the 7th International Symposium on Next Generation Electronics (ISNE), Taipei, pp. 1-4, 2018.
[40]M. Wang, T. Sirlapu, A. Kwasniewska, M. Szankin, M. Bartscherer and R. Nicolas, “Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions,” Proceedings of the 11th International Conference on Human System Interaction (HSI), Gdansk, pp. 139-145, 2018.
[41]B. Shi, “An Intelligent System for English Pronunciation Correction,” Proceedings of the International Conference on Virtual Reality and Intelligent Systems (ICVRIS), Changsha, pp. 255-258, 2018.
[42]B. Lin, H. Huang, R. Sheu and Y. Chang, “Speech Recognition for People with Dysphasia Using Convolutional Neural Network,” Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, pp. 2164-2169, 2018.
[43]E. Franti, I. Ispas and M. Dascalu, “Testing the Universal Baby Language Hypothesis - Automatic Infant Speech Recognition with CNNs,” Proceedings of the 41st International Conference on Telecommunications and Signal Processing (TSP), Athens, pp. 1-4, 2018.
[44]O. Abdel-Hamid, A. Mohamed, H. Jiang, L. Deng, G. Penn and D. Yu, “Convolutional Neural Networks for Speech Recognition,” in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 22, no. 10, pp. 1533-1545, Oct. 2014.
[45]T. Fan, Z. Mu and R. Yang, “Multi-Modality Recognition of Human Face and Ear Based on Deep Learning,” Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), Ningbo, pp. 38-42, 2017.
[46]C. M. A. Ilyas, K. Nasrollahi, M. Rehm and T. B. Moeslund, “Rehabilitation of Traumatic Brain Injured Patients: Patient Mood Analysis from Multimodal Video,” Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), Athens, pp. 2291-2295, 2018.
[47]A. Choromanska, M. Henaff, M. Mathieu, G. B. Arous, and Y. LeCun, “The Loss Surfaces of Multilayer Networks,” in Artificial Intelligence and Statistics, pp. 192-204, 2015.
[48]Y. N. Dauphin, R. Pascanu, C. Gulcehre, K. Cho, S. Ganguli, and Y. Bengio, “Identifying and Attacking the Saddle Point Problem in High-Dimensional Non-Convex Optimization,” in Advances in neural information processing systems, pp. 2933-2941, 2014.
[49]I. J. Goodfellow, O. Vinyals and A. M. Saxe, “Qualitatively Characterizing Neural Network Optimization Problems,” Proceedings of the International Conference on Learning Representations, San Diego, CA, 2015.
[50]A. M. Saxe, J. L. McClelland and S. Ganguli, “Exact Solutions to the Nonlinear Dynamics of Learning in Deep Linear Neural Networks,” Proceedings of the 2nd International Conference on Learning Representations, Banff, Canada, 2014.
[51]I. Goodfellow, Y. Bengio and A. Courville, 。深度学习（Deep learning）（趙申劍、黎彧君、符天凡與李凱譯）（初版）。北京：人民邮电出版社, 2017。
[52]A. Gaber, M. F. Taher and M. A. Wahed, “Quantifying Facial Paralysis Using the Kinect v2,” Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, pp. 2497-2501, 2015.
[53]R. C. Carro, E. B. Huerta, R. M. Caporal, J. C. Hernandez and F. R. Cruz, “Facial Expression Analysis with Kinect for the Diagnosis of Paralysis Using Nottingham Grading System,” in IEEE Latin America Transactions, vol. 14, no. 7, pp. 3418-3426, July 2016.
[54]A. Gaber, M. F. Faher and M. A. Waned, “Automated Grading of Facial Paralysis Using the Kinect v2: A proof of Concept Study,” Proceedings of the International Conference on Virtual Rehabilitation (ICVR), Valencia, pp. 258-264, 2015.
[55]M. Hakata, M. Seo, Y. Chen and N. Matsushiro, “Facial Paralysis Modeling Based on Image Morphing,” Proceedings of the 6th International Conference on Biomedical Engineering and Informatics, Hangzhou, pp. 806-810, 2013.
[56]H. Yoshihara, M. Seo, T. H. Ngo, N. Matsushiro and Y. Chen, “Automatic Feature Point Detection Using Deep Convolutional Networks for Quantitative Evaluation of Facial Paralysis,” 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Datong, pp. 811-814, 2016.
[57]T. H. Ngo, M. Seo, Y. Chen and N. Matsushiro, “Quantitative Evaluation of Facial Paralysis Using Tracking Method,” Proceedings of the IEEE RIVF International Conference on Computing & Communication Technologies - Research, Innovation, and Vision for Future (RIVF), Can Tho, pp. 100-105, 2015.
[58]J. Ahlberg, “Candide-3 - an Updated Parameterised Face,” Technical Report LiTH-ISY-R-2326, Image Coding Group, Dept. of Electrical Engineering, Linkoping University, Sweden, 2001.
[59]Kinect Face Tracking SDK(http://brightguo.com/kinect-face-tracking/)
[60]許晏銘，「基於動態歸化之機器學習方法於小字彙DTW語音辨識系統之研究」，國立虎尾科技大學電機工程學系碩士論文，2013。
[61]Thiang and S. Wijoyo, “Speech Recognition Using Linear Predictive Coding and Artificial Neural Network for Controlling Movement of Mobile Robot,” Proceedings of the International Conference on Information and Electronics Engineering (ICIEE), Bangkok, Thailand, pp. 28-29, 2011.
[62]W. S. M. Sanjaya, D. Anggraeni and I. P. Santika. “Speech Recognition Using Linear Predictive Coding (LPC) and Adaptive Neuro-Fuzzy (ANFIS) to Control 5 DoF Arm Robot,” Proceedings of the International Conference on Computation in Science and Engineering, Malaysia, 2018.
[63]K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, 2015.
[64]B. Selbes and M. Sert, “Multimodal vehicle type classification using convolutional neural network and statistical representations of MFCC,” Proceedings of the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Lecce, pp. 1-6, 2017.
[65]J. Jiang, X. Feng, F. Liu, Y. Xu and H. Huang, “Multi-Spectral RGB-NIR Image Classification Using Double-Channel CNN,” IEEE Access, vol. 7, pp. 20607-20613, 2019.