The accuracy and user acceptance of speech recognition systems is increasing in the last few years especially for automated identification and biomedical applications. In implementation, it works based on the feature of utterance that will be recognized through a feature extraction process. One process in feature extraction is windowing that is done for minimizing the disruptions at the first and last of the frame. Basically, many window functions exist such as rectangular window, flat top window, hamming window, etc, but in the real application only hamming or Hanning function that are usually used as a function in the windowing. This article will analyzed the performance of all of window functions to prove the performance of those function. The method that was used are mel-frequencies cepstral coefficients (MFCCs) as feature extractor technique and back propagation neural networks (BPNNs) as classifier. The result shows that it can produce an accuracy at least 99%. The optimal accuracy up to 99.86% is achieved using rectangle window with the duration of process is 15.47 msec. This results show the superior performance of rectangle window as reference to recognize an isolated word based on speech.