An Algorithm for Locating the Beginning and End of an Utterance Using ADPCM Coded Speech

The need to automatically locate the beginning and end of a speech utterance frequently arises in speech processing for automatic speech recognition and speaker verification. We have also encountered this problem in implementing an automatic vocabulary preparation scheme for a multiline computer voice response system.1 Since our solution to the problem of automatically locating the endpoints of an utterance is based on some unique properties of the adaptive differential PCM (ADPCM) representation of speech waveforms,2 we must first discuss the fundamentals of ADPCM waveform coding.