Patent · US Expired

Automatic determination of labels and Markov word models in a speech recognition system

US5072452A · kind A · utility

276Cited by
19References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 2, 1989
Grant dateDec 10, 1991
Priority date
Expiry dateNov 2, 2009

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/14
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In a Markov model speech recognition system, an acoustic processor generates one label after another selected from an alphabet of labels. Each vocabulary word is represented as a baseform constructed of a sequence of Markov models. Each Markov model is stored in a computer memory as (a) a plurality of states; (b) a plurality of arcs, each extending from a state to a state with a respective stored probability; and (c) stored label output probabilities, each indicating the likelihood of a given label being produced at a certain arc. Word likelihood based on acoustic characteristics is determined by matching a string of labels generated by the acoustic processor against the probabilities stored for each word baseform. Improved models of words are obtained by specifying label parameters and constructing word baseforms interdependently and iteratively.

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