Title :
The challenges of SVM optimization using Adaboost on a phoneme recognition problem
Author :
Amami, Rimah ; Ben Ayed, Dorra ; Ellouze, Noureddine
Author_Institution :
Dept. of Electr. Eng., Univ. of Tunis, El Manar, Tunisia
Abstract :
The use of digital technology is growing at a very fast pace which led to the emergence of systems based on the cognitive infocommunications. The expansion of this sector impose the use of combining methods in order to ensure the robustness in cognitive systems.
Keywords :
learning (artificial intelligence); pattern classification; radial basis function networks; signal classification; speech recognition; support vector machines; Adaboost; MFCC feature representations; SVM optimization; SVM-RBF; TIMIT corpus; adaptive boosting; classification methods; cognitive infocommunications; digital technology; high-performance prediction rule; learning algorithm error reduction; minimal margin maximization; multiclass phoneme recognition problem; performance improvement; phoneme datasets; recognition rates; supervised algorithm; support vector machines; training set; weak classifiers; Accuracy; Boosting; Conferences; Decision trees; Speech; Speech recognition; Support vector machines; Adaboost; C4.5; Optimization; SVM; phoneme;
Conference_Titel :
Cognitive Infocommunications (CogInfoCom), 2013 IEEE 4th International Conference on
Conference_Location :
Budapest
Print_ISBN :
978-1-4799-1543-9
DOI :
10.1109/CogInfoCom.2013.6719292
