Method and apparatus for accessing an audio file from a collection of audio files using tonal matching

摘要

There is provided a method for accessing at least one audio file from a collection comprising more than one audio file stored within or accessible with an electronic device. The method includes generating one index comprising of information entries obtained from each of the more than one audio file in the collection, with each audio file in the collection information being linked to at least one information entry; receiving an input during an input reception mode; converting the input into a digital signal using an analog-digital converter; analyzing the digital signal using either frequency spectrum analysis or melody contour analysis into discrete portions; and comparing the discrete portions with the entries in the index. It is advantageous that the audio file is accessed when the discrete portions substantially coincide with at least one of the information entries in the index. The discrete portions may be musical notes, melody contours or waveforms. The at least one information entry may also be musical notes, melody contours or waveforms. An apparatus employing the aforementioned method is also disclosed.

主权项

1. A non-transitory computer readable medium containing a set of computer executable instructions to perform the steps of:
generating one index comprising of information entries obtained from each audio file in a collection comprising a plurality of audio files, with each audio file in the collection being linked to at least one information entry where the at least one information entry includes, for an audio output for each audio file,
(a) a first order melody contour (UDR) representing difference in pitch between a current note and a previous note,(b) a second order melody contour (udr) representing difference between the first order melody contour of the current note and the previous note, and(c) a duration contour (LSK) for the audio output; receiving an input during an input reception mode; converting the input into a digital signal using an analog-digital converter, the input includes,
(a) a first order melody contour (UDR) representing difference in pitch between a current note and a previous note,(b) a second order melody contour (udr) representing difference between the first order melody contour of the current note and the previous note, and(c) a duration contour (LSK) for the input; analysing the digital signal of the input into discrete portions using melody contour analysis, where the melody contour analysis is based on:
comparing the discrete portions of both the audio output for each audio file with the information entries in the index and the input in order to generate a series of values based on errors between:
the UDR associated with the audio output and the UDR associated with the input;the udr associated with the audio output and the udr associated with the input; andthe LSK associated with the audio output and the LSK associated with the input, generating a “closeness” score for audio file matching, wherein the “closeness” score is obtained by a continuous path with a lowest summation of the values; and wherein the at least one audio file is accessed using the “closeness” score.