Method and apparatus for time series signal recognition with signal variation proof learning

Claim 1

An apparatus for time series signal recognition, comprising: means (1) for inputting signal patterns for time series signals to be recognized; means (2) for recognizing the time series signals, including: means for (6A, 6B) extracting a multiplicity of candidate feature vectors characterizing individual time series signal from the signal pattern, without fixing a boundary for individual time series signal in the signal patterns; recognition dictionary means (7) for storing reference patterns with respect to which the individual time series signals are to be matched; means(6C) for calculating similarity values for each of the multiplicity of candidate feature vectors and the reference patterns stored in the recognition dictionary means(7); and means (8) for determining a recognition result by selecting reference patterns stored in the recognition dictionary means (7) for which the similarity value calculated by the calculating means(6C) is greater than a prescribed threshold value; CHARACTERIZED BY FURTHER COMPRISING: means(3) for learning new reference patterns to be stored in the recognition dictionary means(7), including: means (12) for artificially synthesizing signal patterns with variations for learning to be given to the recognizing means(2); means(14) for extracting feature vectors for learning from the recognition results and the similarity values obtained by the recognizing means (2) from the signal patterns with variations for learning; and means (15) for obtaining the new reference patterns from the feature vectors for learning extracted by the extracting means(14).

Claim 2

An apparatus for time series signal recognition, comprising: means (1) for inputting signal patterns for time series signals to be recognized; means (2) for recognizing the time series signals, including: means for (6A, 6B) extracting a multiplicity of candidate feature vectors characterizing individual time series signal from the signal pattern, without fixing a boundary for individual time series signal in the signal patterns; recognition dictionary means (7) for storing reference patterns with respect to which the individual time series signals are to be matched; means(6C) for calculating similarity values for each of the multiplicity of candidate feature vectors and the reference patterns stored in the recognition dictionary means(7); and means (8) for determining a recognition result by selecting reference patterns stored in the recognition dictionary means (7) for which the similarity value calculated by the calculating means(6C) is greater than a prescribed threshold value; CHARACTERIZED BY FURTHER COMPRISING: means(3) for learning new reference patterns to be stored in the recognition dictionary means(7), including: means (12) for artificially synthesizing signal patterns with variations for learning to be given to the recognizing means(2); means(14) for extracting feature vectors for learning from the recognition results and the similarity values obtained by the recognizing means (2) from the signal patterns with variations for learning; and means (15) for obtaining the new reference patterns from the feature vectors for learning extracted by the extracting means(14).

Claim 7

A method of time series signal recognition, comprising the steps of: inputting signal patterns for time series signals to be recognized; recognizing the time series signals, including the steps of: extracting a multiplicity of candidate feature vectors characterizing individual time series signal from the signal pattern, without fixing a boundary for individual time series signal in the signal patterns; storing reference patterns with respect to which the individual time series signals are to be matched in recognition dictionary means; calculating similarity values for each of the multiplicity of candidate feature vectors and the reference patterns stored in the recognition dictionary means; and determining a recognition result by selecting reference patterns stored in the recognition dictionary means for which the similarity value calculated at the calculating step is greater than a prescribed threshold value; CHARACTERIZED BY FURTHER COMPRISING THE STEPS OF: learning new reference patterns to be stored in the recognition dictionary means, including the steps of: artificially synthesizing signal patterns with variations for learning to be given to the recognizing step; extracting feature vectors for learning from the recognition results and the similarity values obtained by the recognizing step from the signal patterns with variations for learning; and obtaining the new reference patterns from the feature vectors for learning extracted by the extracting step.

Claim 8

A method of time series signal recognition, comprising the steps of: inputting signal patterns for time series signals to be recognized; recognizing the time series signals, including the steps of: extracting a multiplicity of candidate feature vectors characterizing individual time series signal from the signal pattern, without fixing a boundary for individual time series signal in the signal patterns; storing reference patterns with respect to which the individual time series signals are to be matched in recognition dictionary means; calculating similarity values for each of the multiplicity of candidate feature vectors and the reference patterns stored in the recognition dictionary means; and determining a recognition result by selecting reference patterns stored in the recognition dictionary means for which the similarity value calculated at the calculating step is greater than a prescribed threshold value; CHARACTERIZED BY FURTHER COMPRISING THE STEPS OF: learning new reference patterns to be stored in the recognition dictionary means, including the steps of: artificially synthesizing signal patterns with variations for learning to be given to the recognizing step; extracting feature vectors for learning from the recognition results and the similarity values obtained by the recognizing step from the signal patterns with variations for learning; and obtaining the new reference patterns from the feature vectors for learning extracted by the extracting step.