Recognition unit model training based on competing word and word string models
Patent 5579436 Issued on November 26, 1996. Estimated Expiration Date: 
November 26, 2013. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.
November 26, 2013. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.Patent ReferencesRapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker Method of optimizing a composite speech recognition expert Speech recognition system having word-based and phoneme-based recognition means Patent #: 5315689 InventorsApplicationNo. 030895 filed on 03/15/1993US Classes:704/244, Update patterns704/236, Specialized equations or comparisons704/256MarkovExaminersPrimary: Knepper, David D.Attorney, Agent or FirmInternational ClassesG10L 005/04G10L 005/06 AbstractA system pattern-based speech recognition, e.g., a hidden Markov model (HMM) based speech recognizer using Viterbi scoring. The principle of minimum recognition error rate is applied by the present invention using discriminative training. Various issues related to the special structure of HMMs are presented. Parameter update expressions for HMMs are provided. | |
