| dc.description.abstract | Speech recognition is the process ofconverting an acoustic signal, captured by a microphone or a telephone, to a set of words, Speech can be defined as waves of air pressure created by airflow pressed Out of the lungs and going out through the th and nasal cavities, The air passes through the vocal folds (chords) via the path from the lungs through the vocal tract, vibrating them at different frequencies. To make a computer system reacts as a uman elng In recognizing a words no an easy task. A good model is needed to represent the speech signal as the Input ofthe speech system. , . This research used Baum-Welch training algorithm to train HMM as the model of a word. The purpose of this research IS to implement HMM using Baum-Welch training algonthm to recognize an isolated word. Words of this research are ranged into 2 types of syllable: they are 2 syllables and 3 syllables. Speaker ofthis research is also ranged Into 2 trained woman speaker and 2 trained men speaker, therefore this syslern is side to be speaker-dependent. In general this research resulted some HMM . that represent speech signal input as an Indonesian word. The best HMM to recognize an isolated word IS HMM uSing 3 hidden states thaI were trained up to 10 epochs and the best accuracy is 83, 125%. | en |
