電話行銷一直以來都是企業與顧客互動或是發掘潛在顧客的重要環節，透過電話
行銷可以讓企業不必顧慮地理限制，並且相對於傳統的線下走訪推銷，以電話行銷之
方式不止能節省成本的支出，也能更有效率地與顧客互動。根據計畫行為理論以及期
望確認理論顯示，態度及滿意度被視為影響顧客行為決策的重要因素，而顧客的行為
決策則會影響其購買行為以及再購行為，因此顧客之態度及滿意度會是企業成長的重
要因素。
在過去的研究中，要取得顧客之態度及滿意度，都是依靠問卷、焦點團體以及實
地訪談等方式，但這些取得態度及滿意度的方式往往較耗費時間及金錢。所以若是想
要在電話行銷上取得顧客之態度及滿意度，則需要使用更即時的方法，且該方法需要
適用於電話行銷上。而聲學分析的研究及技巧已經被廣泛運用於找出話語中之情感、
情緒以及話語內容，但是還未有研究透過聲學分析之技巧去找出聲音中之態度以及滿
意度，因此本篇論文將聲學分析之技巧應用於瞭解顧客之態度及滿意度，不只能解決
傳統方法較不即時之問題，同時也是第一篇透過聲學分析態度及滿意度之研究。
本研究以實驗設計收集受試者之錄音檔，並將這些錄音檔作為分析之目標，進行 聲學特徵萃取，以及態度及滿意度之程度標記，在聲學處理及分析完後，會透過遞迴 式類神經網路進行分類模型訓練，而本研究態度及滿意度之分類模型精準度皆達 70% 以上，相較於傳統以 SVM 進行分類有更好的精準度。此外，透過本研究可以了解聲音 中之態度及滿意度，未來企業可以將此技術實際應用於電話行銷上，以此方式即時瞭 解顧客之態度及滿意度，是企業能快速挑整策略並提供更好的服務。

Telemarketing has always been an important role for the companies to communicate with customers or searching for the new opportunities. Through Telemarketing, companies can ignore the inconvenience causes by geographical barrier. And according to TPB and ECT model, Attitude and Satisfaction are two of the important factors that influence customers’ behavior. Moreover, Customers behavior can affect their purchasing behavior and repurchasing behavior as well. That being said, Attitude and Satisfaction are one of the most important factors that determine company’s growth rate.
In past research, Attitude and Satisfaction are receiving through questionnaire or focus group. These two methods can’t really give the company real-time data, while in Telemarketing, real -time analyze is an important issue. Furthermore, among the research with Sound, most of them are related to sentiment and emotion. There’s no related work show the connection between sound and attitude or satisfaction. Therefore, this research is using speech analysis to determine customer’s attitude and satisfaction.
We collected data through our own experiment, extract speech feature to label it. Then using RNN and LSTM to train the models to identify customer’s attitude and satisfaction. In the result, we are able to identify attitude and satisfaction through speech with 70% of accuracy. This result is better than traditional SVM classification. Companies can thus apply this method into Telemarketing, to create real-time attitude and satisfaction information while communication. This can provide the company with better strategy within marketing and create a bigger opportunity for the company.

[1] E. Boyd. (1996). Defensive marketing’s use of post-purchase telecommunications to create competitive advantages: a strategic analysis. Journal of Consumer Marketing, vol. 13, Issue 1, pp. 26-34.
[2] Ajzen, I. (1988). Theory of Planned Behavior. Encyclopedia of Social Psychology.
[3] Oliver, R. L. (1980). A Cognitive Model of the Antecedents and Consequences of Satisfaction Decisions. Journal of Marketing Research.
[4] Allport,G.W.(1935)Attitudes.In:Murchison,C.,Ed.,HandbookofSocial Psychology.
[5] Ajzen, I., & Fishbein, M. (1977). Attitude-behavior relations: A theoretical analysis and review of empirical research. Psychological Bulletin.
[6] Fishbein, M. (1966). The Relationships between Beliefs, Attitudes, and Behavior. Cognitive Consistency, pp. 199-223.
[7] Fishbein, M. (1976). A Behavior Theory Approach to the Relations between Beliefs about an Object and the Attitude Toward the Object. Lecture Notes in Economics and Mathematical Systems Mathematical Models in Marketing.
[8] Rokeach, M. (1968). A Theory of Organization and Change Within Value- Attitude Systems. Journal of Social Issues.
[9] Bem, D. J. (1972). Self-Perception Theory. Advances in Experimental Social Psychology Volume 6 Advances in Experimental Social Psychology, pp. 1-62.
[10] Zimbardo, P. G. (1977). Shyness: What it is, what to do about it. Reading, MA: Addison-Wesley.
[11] Kotler, Philip J. (1991). Marketing Management, Seventh Edition, Englewood Cliffs, NJ: Prentice-Hall.
[12] Engel J. F., Blackwell R. D., & Miniard P. W. (1995). Consumer Behavior. 8th, Forth Worth, Dryden Press, Texas.
[13] Hempel, D. J. (1977). Consumer Satisfaction with the Home Buying Process: Conceptualization and Measurement. In The Conceptualization of Consumer Satisfaction and Dissatisfaction.
[14] Hunt, H. K. (1977). CS/D-Overview and Future Research Direction. In H. K. Hunt (ed.), Conceptualization and Measurement of Consumer Satisfaction and Dissatisfaction, pp. 455-488.
[15] Westbrook, R. A. (1980). A Rating Scale for Measuring Product/Service Satisfaction. Journal of Marketing.
[16] Churchill, G. A. & Surprenant, C. (1982). An Investigation Into the Determinants of Customer Satisfaction. Journal of Marketing Research, 19, pp. 133-147.
[17] Smith, R. A., & Houston, M. J. (1983). Script-Based Evaluations of Satisfaction with Services. American Marketing, 23, pp. 99-107.
[18] Woodruff, R. B., Cadotte E. R. & Jenkins R. L. (1993). Modeling Consumer Satisfaction Process Using Experience Based Norms. Journal of Marketing.
[19] Woodruff, R.B., Ernest R. C. & Roger J. L. (1983). Modeling Consumer Satisfaction Processes Using Experience-Based Norms. Journal of Marketing Research
[20] Spreng, R. A. & Mackoy, R. D. (1996). An Empirical Examination for a Model Perceived Serviced Quality and Satisfaction. Journal of Retailing.
[21] Nyer, P. U. (1997). A Study of the Relationships. Between Cognitive Appraisals and Consumption Emotions. Academy of Marketing Science, 25(4), pp. 296-304.
[22] Tsiros, M. & Mittal, V. (2000). A Model of Its Antecedents and Consequences in Consumer Decision Making. Journal of Consumer Research.
[23] Oliver, R. L., & Desarbo, W. S. (1988). Response Determinants in Satisfaction Judgments. Journal of Consumer Research.
[24] Tzirakis, P., Zhang, J., & Schuller, B. W. (2018). End-to-End Speech Emotion Recognition Using Deep Neural Networks. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[25] Jiang, D., & Cai, L. (n.d.). Speech emotion classification with the combination of statistic features and temporal features. 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).
[26] Schuller, B., Rigoll, G., & Lang, M. (n.d.). Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[27] Busso, C., Deng, Z., Yildirim, S., Bulut, M., Lee, C. M., Kazemzadeh, A., Narayanan, S. (2004). Analysis of emotion recognition using facial expressions, speech and multimodal information. Proceedings of the 6th International Conference on Multimodal Interfaces - ICMI 04.
[28] Nwe, T. L., Foo, S. W., & Silva, L. C. (2003). Speech emotion recognition using hidden Markov models. Speech Communication, 41(4), pp. 603-623.
[29] Moriyama, T., & Ozawa, S. (n.d.). Emotion recognition and synthesis system on speech. Proceedings IEEE International Conference on Multimedia Computing and Systems.
[30] Fukuda, S., & Kostov, V. (n.d.). Extracting emotion from voice. IEEE SMC99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).
[31] Ayadi, M. E., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognition.
[32] Yildirim, S., & Narayanan, S. (2009). Automatic Detection of Disfluency Boundaries in Spontaneous Speech of Children Using Audio–Visual Information. IEEE Transactions on Audio, Speech, and Language Processing, 17(1), pp. 2-12.
[33] Bertero, D., Siddique, F. B., Wu, C., Wan, Y., Chan, R. H., & Fung, P. (2016). Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.
[34] Yu, F., Chang, E., Xu, Y., & Shum, H. (2001). Emotion Detection from Speech to Enrich Multimedia Content. Advances in Multimedia Information Processing — PCM 2001 Lecture Notes in Computer Science, pp. 550-557.
[35] Maghilnan, S., & Kumar, M. R. (2017). Sentiment analysis on speaker specific speech data. 2017 International Conference on Intelligent Computing and Control (I2C2).
[36] Kaushik, L., Sangwan, A., & Hansen, J. H. (2013). Automatic sentiment extraction from YouTube videos. 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
[37] Souraya Ezzat, Neamat El Gayar, & Moustafa M. Ghanem. (2012). Sentiment Analysis of Call Centre Audio Conversations using Text Classification. International Journal of Computer Information Systems and Industrial Management
Applications, 4 (2012), pp. 619-627
[38] Campbell, J. (1997). Speaker recognition: A tutorial. Proceedings of the IEEE, 85(9), pp. 1437-1462.
[39] Allen, J. B. (1995). How do Humans Process and Recognize Speech? Modern Methods of Speech Processing, pp. 251-275.
[40] Wilpon, J. G., Mikkilineni, R. P., Roe, D. B., & Gokcen, S. (1990). Speech Recognition: From the Laboratory to the Real World. AT&T Technical Journal.
[41] Graves, A., Mohamed, A., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.
[42] Davis, K. H., Biddulph, R., & Balashek, S. (1952). Automatic Recognition of Spoken Digits. The Journal of the Acoustical Society of America, 24(6), pp. 637-642.
[43] Taylor, S., & Todd, P. A. (1995). Understanding Information Technology Usage: A
Test of Competing Models. Information Systems Research, 6(2), 144-176.
[44] Bhattacherjee, A. (2001). Understanding Information Systems Continuance: An
Expectation-Confirmation Model. MIS Quarterly.
[45] Le, P. N., Sethu, V., Ambikairajah, E., & Kua, J. M. (2011). Investigation of the
robustness of a non-uniform filterbank for cognitive load classification. 2011 8th
International Conference on Information, Communications & Signal Processing.
[46] Singh, N., Khan, R. A., & Shree, R. (2012). MFCC and Prosodic Feature Extraction
Techniques: A Comparative Study. International Journal of Computer
Applications, pp. 9-13.
[47] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural
Computation, 9(8), pp. 1735-1780.
[47] 李俊昇、黃珠娟、許馨仁、林明慧, (2010). 語音情緒辨識技術與應用之研究. 台 灣感性學會研討會論文.
[48] Praat. Retrieved from http://www.fon.hum.uva.nl/praat/