In this paper, we show some the implementation issues of automatic speech recognition (ASR) for portable devices. First, we propose free-running speech recognition software which does not need to push the button before saying voice command and is always running for detecting key-words under real environment. Second, we propose a method for detecting keyword and rejecting out-of-vocabularies (OOV). It consists of filler-modeling technique and utterance verification. And finally, we implement the ASR software on PDAs (Samsung SPH-M4300 and HP iPAQ-RW6100), one kind of portable devices. It works in 54.7% of real-time with the recognition accuracy of 88.3%.