In integrating multi-isolated-word recognizers into a speech recognition for variousstressed speeches, the best likelihood scopes as outputs of each recognizer are notguaranteed a correct recognition result. Since training sometimes does not cover all speakers,likelihood score of the correct recognition result is not the best and causes misrecognition.Moreover, the difference among recognizers also leads to mis-understanding. This paperproposes a decision-making method for Thai stressed speech recognition with parallel hiddenMarkov model. In this method, a voting scheme is applied on the words with the N-bestlikelihood score. Firstly, if the score margin between the first and the second-best is greaterthan a threshold, the voting is applied on the words with highest scores from each recognizer.If there is no clear winner, decided by considering the voting score, the next best score areincluded into the voting scheme. The process goes on until a winner is found or there is a tiedscore, its which case the average of the likelihood score of each tied word is used to decidethe winner. The experiments were conducted with 4-stress speeches including angry, toward,loud, and neutral. It showed that the proposed method helped increase the recognition rate to96.545% comparing with previous decision making techniques.