Measuring Customer Satisfaction through Speech Using Valence-Arousal Approach

There had been many empirical researched demonstrating the important link between customer satisfaction and sales performance, as such many Customer Satisfaction index (CSI) were developed. Almost all CSI to date uses the survey or questionnaire method, which has its flaws. In order to quantify the CSI, we propose the use of speech analysis based on the affective space model where the valence and arousal of the customer can be extracted, indicating their immediate emotion. Speech were recorded and relevant features extracted using Mel Frequency Cepstral Coefficient (MFCC) coupled with Adaptive Neuro Fuzzy Inference System (ANFIS) with subtractive clustering for classification. The network were trained to responds to the two dimensional Affective Space Model (ASM) classification which consist of valence and arousal. Further analysis were carried out to understand the impact of neutral on the accuracy of the classification. Experimental results show that recognition rate for measuring satisfaction is 40% and neutral emotion obtained the highest recognition with 58%. Such analysis can help in understanding the satisfaction and dissatisfaction of customers based on speech with improving the accuracy.

[1]  Muslim Amin,et al.  The role of customer satisfaction in enhancing customer loyalty in Malaysian Islamic banks , 2011 .

[2]  Veronica Liljander,et al.  Emotions in service satisfaction , 1997 .

[3]  H. Schlosberg.  Three dimensions of emotion. , 1954, Psychological review.

[4]  M. Hamidi,et al.  ECOGNITION FROM P ERSIAN S PEECH WITH N EURAL N ETWORK , 2012 .

[5]  Abdul Wahab,et al.  Human behavior state profile mapping based on recalibrated speech affective space model , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Abdul Wahab,et al.  Features extraction for speech emotion , 2008, J. Comput. Methods Sci. Eng..

[7]  Laurence Devillers,et al.  Real-Life Emotion Recognition in Speech , 2007, Speaker Classification.

[8]  Hiok Chai Quek,et al.  Cultural dependency analysis for understanding speech emotion , 2012, Expert Syst. Appl..

[9]  Yixiong Pan,et al.  SPEECH EMOTION RECOGNITION USING SUPPORT VECTOR MACHINE , 2010 .

[10]  Nikos Fakotakis,et al.  Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task , 2007 .

[11]  L. F. Barrett.  Discrete Emotions or Dimensions? The Role of Valence Focus and Arousal Focus , 1998 .

[12]  J. Sitzia,et al.  Good practice in the conduct and reporting of survey research. , 2003, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[13]  Fakhri Karray,et al.  Survey on speech emotion recognition: Features, classification schemes, and databases , 2011, Pattern Recognit..

[14]  Abdul Wahab,et al.  CMAC for speech emotion profiling , 2009, INTERSPEECH.

[15]  Abdul Wahab,et al.  Real Time Driving Data Collection and Driver Verification using CMAC-MFCC , 2008, IC-AI.

[16]  Shrikanth S. Narayanan,et al.  Toward detecting emotions in spoken dialogs , 2005, IEEE Transactions on Speech and Audio Processing.

[17]  Youngja Park,et al.  Towards real-time measurement of customer satisfaction using automatically generated call transcripts , 2009, CIKM.

[18]  P. Ekman.  An argument for basic emotions , 1992 .

[19]  Nishu Sharma,et al.  A Comparative Study Of Data Clustering Techniques , 2013 .

[20]  Pierre Dumouchel,et al.  Anchor Models for Emotion Recognition from Speech , 2013, IEEE Transactions on Affective Computing.

[21]  Ashok K. Sinha,et al.  An Empirical Model of Regional Growth using Adaptive Neuro-Fuzzy Inference System , 2015 .

[22]  Dieter Hoffmann,et al.  Online, face-to-face and telephone surveys—Comparing different sampling methods in wine consumer research , 2013 .

[23]  Norhaslinda Kamaruddin,et al.  Valence-arousal approach for speech emotion recognition system , 2013, 2013 International Conference on Electronics, Computer and Computation (ICECCO).

[24]  J. Russell,et al.  The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology , 2005, Development and Psychopathology.