Vowel recognition is the main topic in speech recognition. There are sixIndonesian vowels, i.e. /a/, /i/, /u/, /e/, /ə/ and /o/. Feature extraction is an importantstep in recognition system because the recognition rate depends on featureextraction results. Vowel feature extraction via discrete wavelet transform (DWT) ispresented here. Mother wavelet db4 and sym4 are used. Minimum, maximum, meanand standard deviation value of wavelet coefficients are extracted as vowel features.DWT with level 2 decomposition obtains 12 features, level 4 decomposition obtains20 features and level 6 decomposition obtains 28 features. Then, those vowelfeatures are used as an input of artificial neural network (ANN) with 2 hidden layers.First hidden layer has 10 neurons and second hidden layer has variety 5 and 7neurons. Backpropagation method is used to train the ANN. The vowel signals arerecorded from 10 female respondens and 10 male respondens. Each respondenpronounces six Indonesian vowels and syllable /ka/, /ki/, /ku/, /ke/, /kə/ and /ko/.Experimental results show that the best recognition rate for the vowel is 85%, whichis obtained by using mother wavelet sym4, level 6 decomposition and 7 neurons forsecond hidden layer, and the best recognition rate for the syllable is 80%, which isobtained by using mother wavelet db4, level 6 decomposition and 5 neurons forsecond hidden layer.