Patent · US Expired

Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments

US4819271A · kind A · utility

273Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 16, 1987
Grant dateApr 4, 1989
Priority date
Expiry dateDec 16, 2007

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/144
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present invention relates to apparatus and method for segmenting multiple utterances of a vocabulary word in a consistent and coherent manner and determining a Markov model sequence for each segment. A fenemic Markov model corresponds to each label.

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