On the determination of speech boundaries: A tool for providing anchor time points in speech recognition

The objective of the paper is to describe an algorithm for finding robust speech boundaries which can be used as a first step in an acoustic-phonetic-based speech recognition scheme. This algorithm uses information about the speech processing made by the peripheral auditory system. The algorithm has been tested with success with a set of monosyllabic CVC words in English including all the combinations between eleven different consonants and three different vowels. It can find all the vowel onsets, vowel offsets and stop releases for these words.