The visiBabble system processes infant vocalizations in real-time. It responds to the infant's syllable-like productions with brightly colored animations and records the acoustic-phonetic analysis. The system reinforces the production of syllabic utterances that are associated with later language and cognitive development.

The Early Vocalization Analyzer (EVA) is a computer program that automatically analyzes digitized acoustic recordings of infant vocalizations. Using the landmark detection theory of Stevens et al for the recognition of phonetic features in speech, EVA detects syllables in vocalizations produced by infants. Landmarks are grouped into standard syllable patterns and syllables are grouped into utterances. Statistics derived from these groups and the underlying features are used to derive a "vocalization age" that can clinically distinguish infants who may be at risk for later communication or other developmental problems from typically developing infants in the six to fifteen month age range.

Reading Aloud is software to help beginning readers use appropriate prosody while reading out loud. It will provide readers with visual prosodic cues for reading out loud. The software will guide readers through a series of modules that introduce one prosodic feature (duration, loudness, or pitch) at a time. Each prosodic feature will correspond to a given visual cue. An adult model will be used to develop the target prosody.

We have and continue to collect and digitize samples of infant vocalizations. We are starting to build a corpora (database) of these vocalizations. We have transcriptions of the recordings and information on which samples contain particular kinds of sounds, e.g. fricatives or high vowels. We plan to enlarge this corpora and make it searchable so that we can automatically try new feature detection code on samples with a particular feature.