A Statistical Model for Word Discovery in Transcribed Speech

English speech lacks the acoustic analog of blank spaces that people are accustomed to seeing between words in written text. Discovering words in continuous spoken speech then is an interesting problem that has been treated at length in the literature. The issue is particularly prominent in the parsing of written text in languages that do not explicitly include spaces between words, and in the domain of child language acquisition if we assume that children start out with little or no knowledge of the inventory of words the language possesses. While it is undoubtedly the case that although speech lacks explicit demarcation of word boundaries, it nevertheless possesses significant other cues for word discovery, it is still a matter of interest to see exactly how much can be achieved without the incorporation of these other cues, that is, we are interested in the performance of a bare-bones language model. For example, there is much evidence that stress patterns (Jusczyk, Cutler, and Redanz, 1993; Cutler and Carter, 1987) and phonotactics of speech (Mattys and Jusczyk, 1999) are of considerable aid in word discovery. But a bare-bones