<![CDATA[English has become an international language used in various fields, including education, business, and tourism. Indonesia, having become a member of the AEC (Asean Economic Community), makes it increasingly important for Indonesian society, especially the younger generation, to master English proficiently and accurately. English, as an international language, encompasses numerous dialects, such as British and American dialects. This research is motivated by the issue that differences between British and American English dialects can affect understanding and communication in educational, business, and everyday life contexts. Identifying and classifying dialects in English speech is crucial to aid both native and non-native speakers in better understanding communication contexts. This study aims to develop a classification method using the Support Vector Machine (SVM) algorithm to distinguish between British and American English dialects in speech. By leveraging SVM, this research will attempt to identify linguistic features that differentiate between these dialects, such as intonation, vowels, consonants, and rhythm patterns obtained from sound feature extraction using Mel Frequency Cepstral Coefficients (MFCC). In this model training phase, a dataset comprising 720 speech samples collected from various text-to-speech service provider websites is utilized to represent both dialects. Subsequently, the trained model is tested using 24 test data collected from original recordings of several individuals to evaluate its accuracy. The results of this research yield an accuracy rate of 91.6% on the model with a configuration of Cost value 1, gamma 0.001, and polynomial kernel. From these results, it can be concluded that this model exhibits a sufficiently high accuracy, with 2 misclassifications out of 24 test data.]]>
