Patent · US Active

System and method of using meta-data in speech processing

US7996224B2 · kind B2 · utility

17Cited by
5References
30Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 29, 2004
Grant dateAug 9, 2011
Priority date
Expiry dateJan 8, 2028

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2015/228
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods relate to generating a language model for use in, for example, a spoken dialog system or some other application. The method comprises building a class-based language model, generating at least one sequence network and replacing class labels in the class-based language model with the at least one sequence network. In this manner, placeholders or tokens associated with classes can be inserted into the models at training time and word/phone networks can be built based on meta-data information at test time. Finally, the placeholder token can be replaced with the word/phone networks at run time to improve recognition of difficult words such as proper names.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.