Language models for a spelled letter recognizer

In some speech recognition applications, it is reasonable to constrain the search space of a speech recognizer to a large but finite set of sentences. We demonstrate the problem on a spelling task, where the recognition of continuously spelled last names is constrained to 110000 entries (=43000 unique names) of a telephone book. Several techniques to address this problem are compared: recognition without any language model, bigrams, functions to map a hypothesis onto a legal string, n-best lists, and finally a newly developed method which integrates all constraints directly into the search process within reasonable memory and time bounds. The baseline result of 56% string accuracy is improved to 62, 85, 88, and 92%, respectively