Abstract: An audio file is transformed into a Gabor spectrogram. This is used to compare the audio file to a database of audio files, each represented as a Gabor spectrogram. Before two spectrograms are compared, they are aligned. The spectrograms are broken into blocks and individual Gabor vectors in the blocks are compared. Similarities are stored and an aggregate similarity value is derived for the block. After a series of such comparisons and shifting of the secondary spectrogram block, essentially a running window, an offset value is determined. This offset is used to align the two spectrograms at which stage the spectrograms can be compared in a more effective and meaningful manner. A set of observables is derived from the comparisons and the primary spectrogram is classified in way suitable for the application environment.
Abstract: A balanced survey is automatically created in real time, that is, while potential survey participants are evaluated. A survey histogram is automatically re-balanced with each new entry accepted as a respondent. An individual fills out a questionnaire providing demographic and socio-economic data. A vector representation of that person, referred to as an entry, is created. A similarity value is calculated indicating the similarity between the vector representation and a histogram vector representing the make-up of the survey. The similarity value is calculated by taking a dot product of the entry vector representation and the histogram vector. The system then determines whether the similarity value is greater than a similarity threshold value. If the similarity value exceeds the threshold value, the entry vector is integrated into the histogram vector, that is, the individual becomes part of the survey group.
Abstract: An audio file is transformed into a Gabor spectrogram. This is used to compare the audio file to a database of audio files, each represented as a Gabor spectrogram. Before two spectrograms are compared, they are aligned. The spectrograms are broken into blocks and individual Gabor vectors in the blocks are compared. Similarities are stored and an aggregate similarity value is derived for the block. After a series of such comparisons and shifting of the secondary spectrogram block, essentially a running window, an offset value is determined. This offset is used to align the two spectrograms at which stage the spectrograms can be compared in a more effective and meaningful manner. A set of observables is derived from the comparisons and the primary spectrogram is classified in way suitable for the application environment.
Abstract: A balanced survey is automatically created in real time, that is, while potential survey participants are evaluated. A survey histogram is automatically re-balanced with each new entry accepted as a respondent. An individual fills out a questionnaire providing demographic and socio-economic data. A vector representation of that person, referred to as an entry, is created. A similarity value is calculated indicating the similarity between the vector representation and a histogram vector representing the makeup of the survey. The similarity value is calculated by taking a dot product of the entry vector representation and the histogram vector. The system then determines whether the similarity value is greater than a similarity threshold value. If the similarity value exceeds the threshold value, the entry vector is integrated into the histogram vector, that is, the individual becomes part of the survey group.