This paper presents a novel model that learns and exploits embeddings of phone ngrams for word segmentation in child language acquisition. Embedding-based models are evaluated on a phonemically transcribed corpus of child-directed speech, in comparison with their symbolic counterparts using the common learning framework and features. Results show that learning embeddings significantly improves performance. We make use of extensive visualization to understand what the model has learned. We show that the learned embeddings are informative for both word segmentation and phonology in general.