Patent Number: 7,103,544

Title: Method and apparatus for predicting word error rates from text

Abstract: A method of modeling a speech recognition system includes decoding a speech signal produced from a training text to produce a sequence of predicted speech units. The training text comprises a sequence of actual speech units that is used with the sequence of predicted speech units to form a confusion model. In further embodiments, the confusion model is used to decode a text to identify an error rate that would be expected if the speech recognition system decoded speech based on the text.

Inventors: Mahajan; Milind (Redmond, WA), Deng; Yonggang (Towson, MD), Acero; Alejandro (Bellevue, WA), Gunawardana; Asela J. R. (Seattle, WA), Chelba; Ciprian (Seattle, WA)

Assignee: Microsoft Corporation

International Classification: G10L 15/06 (20060101); G10L 15/14 (20060101)

Expiration Date: 9/05/02018