Abstract
Human emotion recognition subject becomes important due to it's usability in daily lifestyle which requires human and computer interraction. Human emotion recognition is a complex problem due to the difference within custom tradition and specific dialect which exists on different ethnic, region and community. This problem also exacerbated due to objectivity assessment for the emotion is difficult since emotion happens unconsciously. This research conducts an experiment to discover pattern of emotion based on feature extracted from speech. Method used for feature extraction on this experiment is Mel-Frequency Cepstral Coefficient (MFCC) which is a method that similar to the human hearing system. Dataset used on this experiment is Berlin Database of Emotional Speech (Emo-DB). Emotions that are used for this experiments are happiness, boredom, neutral, sad and anger. For each of these emotion, 3 samples from Emo-DB are taken as experimental subject. The emotion patterns are successfully visible using specific values for MFCC parameters such as 25 for frame duration, 10 for frame shift, 0.97 for preemphasis coefficient, 20 for filterbank channel and 12 for ceptral coefficients. MFCC features are then extracted and calculated to find mean values from these parameters. These mean values are then plotted based on timeframe graph to be investigated to find the specific pattern which appears from each emotion. Keywords— Emotion, Speech, Mel-Frequency Cepstral Coefficients (MFCC).
Highlights
Human emotion recognition subject becomes important due to it's usability in daily lifestyle which requires human and computer interraction
specific dialect which exists on different ethnic, region and community
to objectivity assessment for the emotion is difficult since emotion happens
Summary
Emosi adalah suatu perasaan yang dirasakan setiap individu dalam intensitas yang tinggi terhadap seseorang atau sesuatu keadaan. Penelitianpenelitian tersebut menggunakan dataset ucapan yang tersedia sebagai standar seberapa baik sebuah sistem melakukan pengenalan emosi. Adapun beberapa penelitian yang dilakukkan untuk mengenali emosi diantaranya, penelitian untuk pengenalan emosi melalui ucapan yang didasarkan dengan objek pengujian Emo-DB [2] menggunakan fitur energi, entropi, MFCC (Mel-Frequency Cepstral Coefficients), ZCC, dan pitch dengan algoritma K-NN (K-Nearsest Neighhor) sebagai pengklasifikasi mencapai akurasi 86.02%. Kemudian penelitian serupa juga dilakukan [3] untuk mengembangkan sistem pengenalan emosi menggunakan beberapa metode dan mencapai akurasi tertinggi sebesar 92% menggunakan GMM (Gaussian Mixture Model), dan 72% menggunakan K-NN untuk emosi marah. Penelitian ini dilakukan untuk mencari pengenalan pola emosi berdasarkan ucapan dengan melakukan ekstraksi fitur ucapan manusia untuk mengetahui ciri polanya [5]. Harapannya adalah hasil dari pengenalan pola emosi ini sistem dapat melakukan pengenalan emosi manusia berdasarkan ucapan [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
