Patent · US Active

Speech recognition system, method and program that generates a recognition result in parallel with a distance value

US7930180B2 · kind B2 · utility

2Cited by
7References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 12, 2006
Grant dateApr 19, 2011
Priority date
Expiry dateSep 8, 2028

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/34
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Speech recognition is performed at high speed by processing respective paths of multi-path speech recognition in parallel. A distance calculation unit receives temporal data sequence of acoustic features, calculates the distance values between all acoustic models and the speech features in the respective frames, and writes them in a distance value buffer. An acoustic lookahead unit receives distance values from a plurality of distance value buffers, calculates lookahead values which are relative priorities of respective recognition units, and writes them into the lookahead value buffer. A word string matching unit receives information from a plurality of distance value buffers and the lookahead value buffers, and recognizes the entire utterance in frame synchronization by adequately selecting matching words using the lookahead values to thereby generate a recognition result.

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