Speech comparison in the Rosetta Stone#8482;
John R. C. Fairfield · 1999
The Rosetta Stone™ is a successful CD-ROM based interactive program for teaching foreign languages, that uses speech comparison to help students improve their pronunciation. The input to a speech comparison system is N+1 digitised utterances. The output is a measure of the similarity of the last utterance to each of the N others. Which language is being spoken is irrelevant. This differs from classical speech recognition where the input data includes but one utterance, a set of expectations tuned to the particular language in use (typically digraphs or similar), and a grammar of expected words or phrases, and the output is recognition in the utterance of one of the phrases in the grammar (or rejection). This paper describes a speech comparison system and its application in The Rosetta Stone™.