Accuracy model for recognition signal processing engines

   
   

Signals to be processed are categorized based on signal characteristics such as physical aspects, context, conditions under which the signals were generated and source, and/or based on other variables. Categorized sets of signals are processed, and an accuracy for each set calculated. Weights are then applied to accuracy values for the sets, and the weighted values summed. In some cases, certain sums are then weighted and further summed.

 
Web www.patentalert.com

< System and method for designing a logical model of a distributed computer system and deploying physical resources according to the logical model

< Synonymous collocation extraction using translation information

> Speech-related event notification system

> Method for lifetime tracking of intellectual property

~ 00187