×

Method of recognizing spoken language with recognition of language color

  • US 7,280,964 B2
  • Filed: 12/31/2002
  • Issued: 10/09/2007
  • Est. Priority Date: 04/21/2000
  • Status: Expired due to Term
First Claim
Patent Images

1. A method of recognizing spoken language, comprising:

  • (a) collecting a plurality of spoken language samples for a word or phrase, each of said plurality of samples being associated with a language color, optionally a regional pronunciation, a mispronunciation, an emotion or Lessac energy;

    (b) processing said spoken language samples into a database suitable for input into a speech recognition system, said database comprising a plurality of graphemes, each of said graphemes comprising a written representation of its associated spoken language sample or phoneme, said database comprising a color associated with at least one of said graphemes;

    (c) receiving speech to be recognized and processing said speech to be recognized for input into a speech recognition system;

    (d) inputting a first portion of said processed speech to be recognized into a speech recognition system, said speech recognition system selecting among processed spoken language samples of different color but corresponding to the same graphemes to obtain a best match to a particular processed language sample and an associated recognized grapheme;

    (e) outputting said recognized graphemes from the speech recognition system;

    (f) inputting a second portion of said processed speech into the speech recognition system, said speech recognition system, at least initially, limiting its selection among processed spoken language samples to processed spoken language samples of a single color, to efficiently obtain a best match to a particular processed language sample and an additional associated recognized grapheme; and

    (g) outputting said additional recognized grapheme from the speech recognition system.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×