Automatic babble recognition for early detection of speech related disorders

We have developed a program, the Early Vocalization Analyzer (EVA), that analyses digitized recordings of infant vocalizations. The purpose of such a system is to automatically and reliably screen infants who may be at risk for later communication problems. EVA applies the landmark detection theory of Stevens et al., for the recognition of acoustic features in adult speech, to detect syllables in vocalizations produced by typically developing six to thirteen month old infants. We discuss the differences between adult-specific code and code written to analyse infant vocalizations. In a validity test, EVA achieved 90% agreement in marking 128 landmarks commonly identified by two human judges, was often closer to one or both judges than the humans were to each other. In a second test EVA and a human judge had 86% agreement in identifying 150 landmarks.